© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8293
    Prev
    Next
    INDEX
    Explanations

    encoding and notation systems

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects technical identifiers and resource labels—terms like file names, addresses (e.g. IP addresses), and related metadata in technical documentation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    technical or instructional text about file formats, naming conventions, and system specifications.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    technical jargon from computing and engineering, especially terms about files, networks, data formats, and software components.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     escuch
    0.68
     पृष्ठभूमि
    0.61
     실행
    0.61
     escucha
    0.61
     testAvg
    0.59
    scrollHeight
    0.58
     hören
    0.57
    рующий
    0.57
     escuchar
    0.57
     ejecuta
    0.57
    POSITIVE LOGITS
     numbering
    1.48
     notation
    1.46
     alphanumeric
    1.39
     coding
    1.38
     symbols
    1.36
     encoding
    1.34
     conventions
    1.34
     identifiers
    1.32
     Notation
    1.30
     naming
    1.30
    Activations Density 0.555%

    No Known Activations