© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 84639
    Prev
    Next
    INDEX
    Explanations

    signing documents and agreements

    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_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
    .
    -2.63
     “
    -2.06
    </h3>
    -2.05
    {
    -1.81
    <strong>
    -1.80
     oh
    -1.80
     /
    -1.78
     "
    -1.74
    </strong>
    -1.73
     :
    -1.71
    POSITIVE LOGITS
    喁
    2.28
     nettsted
    2.17
    欵
    2.11
    _));
    2.08
    豨
    2.06
     männer
    2.02
     valentín
    1.98
     huf
    1.97
    有著
    1.96
     經典
    1.95
    Activations Density 0.032%

    No Known Activations