© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 38185
    Prev
    Next
    INDEX
    Explanations

    code identifiers and structure

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

    This neuron fires on single-token programming identifiers that combine multiple words—e.g. CamelCase names or underscore-separated function/constant names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    COND
    -0.65
    Hayes
    -0.65
    nosed
    -0.64
    зяй
    -0.63
     discovery
    -0.63
     SED
    -0.63
     Puy
    -0.61
    واء
    -0.61
     Sequences
    -0.61
     сла
    -0.61
    POSITIVE LOGITS
     Langkah
    0.75
     ağı
    0.75
    takes
    0.71
    inkl
    0.69
     drau
    0.68
    makta
    0.68
    straint
    0.67
     carico
    0.66
    이며
    0.66
    too
    0.65
    Activations Density 0.047%

    No Known Activations