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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27639
    Prev
    Next
    INDEX
    Explanations

    sanitization and transport

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

    text describing procedures, instructions, or technical requirements related to handling physical objects.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects procedural or instructional language—verbs and “to” phrases that introduce steps or directions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     mehreren
    -1.36
     extensão
    -1.32
     černá
    -1.32
     interesantes
    -1.30
     कई
    -1.28
     zís
    -1.27
    himo
    -1.27
     كما
    -1.27
     modrá
    -1.27
    Muito
    -1.26
    POSITIVE LOGITS
    edade
    1.47
     bobina
    1.43
     adequate
    1.37
     during
    1.33
    āt
    1.32
    strtotime
    1.32
     adequately
    1.31
     use
    1.31
    rekli
    1.30
     when
    1.30
    Activations Density 0.008%

    No Known Activations