© 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. 92717
    Prev
    Next
    INDEX
    Explanations

    event listeners

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     construcción
    -0.76
     DESCRIP
    -0.73
     Interpreting
    -0.72
    ッタ
    -0.72
    ulen
    -0.70
     ettiği
    -0.70
    フィール
    -0.69
    _*
    -0.69
     Outback
    -0.69
    之色
    -0.68
    POSITIVE LOGITS
    Listener
    1.05
    jumu
    1.00
     listener
    0.95
     Listener
    0.89
    ChangeListener
    0.82
     NATO
    0.82
    GIUM
    0.81
    listener
    0.79
     graze
    0.78
    ClickListener
    0.77
    Activations Density 0.010%

    No Known Activations