© 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. 128824
    Prev
    Next
    INDEX
    Explanations

    president Bush

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

    The neuron activates on occurrences of the word “Bush,” flagging mentions of that proper name.

    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
    蕺
    -3.33
    翃
    -3.06
    푆
    -2.64
    鹋
    -2.58
    訁
    -2.56
    嵎
    -2.42
    ⩴
    -2.41
    榦
    -2.39
    沵
    -2.30
     diminu
    -2.28
    POSITIVE LOGITS
    {
    3.17
    y
    2.86
     Desember
    2.48
    L
    2.44
    s
    2.39
     taką
    2.39
    $,
    2.38
     miłości
    2.31
    其他
    2.30
     wszyst
    2.28
    Activations Density 0.004%

    No Known Activations