© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70856
    Prev
    Next
    INDEX
    Explanations

    go or come followed by action

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

    The neuron fires on second-person imperative action words (e.g. “go,” “come”) directing the reader to do something.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     that
    -2.11
    on
    -1.90
     hingga
    -1.71
     många
    -1.54
     many
    -1.49
     resurrection
    -1.46
     memakai
    -1.44
     {
    -1.41
     gdy
    -1.41
    indest
    -1.40
    POSITIVE LOGITS
    Отзывы
    1.75
     报告
    1.56
     μόνο
    1.56
     territ
    1.53
    ၞ
    1.52
    ONLY
    1.50
     hispan
    1.48
     domina
    1.46
    だけ
    1.41
    Empereur
    1.41
    Activations Density 0.015%

    No Known Activations