© 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. 34541
    Prev
    Next
    INDEX
    Explanations

    button and fastening

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

    The neuron spikes on occurrences of the word “button” (in any context, e.g. clothing buttons, UI button events, or proper names containing “Button”).

    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
    ⡄
    -0.82
     township
    -0.79
    ใบ
    -0.77
    anth
    -0.77
    ալ
    -0.75
    ЧЕСКИ
    -0.75
     homeowner
    -0.75
     townships
    -0.75
     HDR
    -0.74
    torem
    -0.74
    POSITIVE LOGITS
     buttons
    3.16
     button
    2.73
    buttons
    2.33
     Buttons
    2.33
    Buttons
    2.17
    button
    2.14
     Button
    2.13
    ボタン
    2.11
     BUTTON
    2.02
    Button
    2.00
    Activations Density 0.011%

    No Known Activations