© 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. 34-GEMMASCOPE-RES-131K
    7. 3023
    Prev
    Next
    INDEX
    Explanations

    buttons and file selection

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

    The neuron is triggered by numeric constants (digit sequences) in code or technical specifications.

    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
    моби
    -0.82
    diğim
    -0.80
     ambulatory
    -0.79
     デスク
    -0.79
     lukewarm
    -0.78
     rehearing
    -0.77
     Kirsch
    -0.75
     Spisak
    -0.75
     daž
    -0.75
     الوا
    -0.75
    POSITIVE LOGITS
     buttons
    1.30
     Button
    1.29
     button
    1.24
    Button
    1.21
    button
    1.20
    buttons
    1.17
     shoulder
    1.16
    ボタン
    1.09
    start
    1.08
    select
    1.05
    Activations Density 0.014%

    No Known Activations