© 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. 14716
    Prev
    Next
    INDEX
    Explanations

    info

    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
     dritten
    -2.17
     mehrere
    -2.08
    UCIÓN
    -2.05
     Zweiten
    -2.03
     thier
    -1.95
    ,
    -1.91
    </b>
    -1.89
    icznej
    -1.88
    发言
    -1.88
    (),
    -1.86
    POSITIVE LOGITS
    铪
    2.09
     jaya
    1.91
     menyen
    1.81
    .
    1.77
     kwamba
    1.77
     This
    1.76
     uchiha
    1.73
    嗞
    1.73
     vald
    1.71
     sufrió
    1.70
    Activations Density 0.015%

    No Known Activations