© 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. 38972
    Prev
    Next
    INDEX
    Explanations

    Kilkenny Lek datatype Playlist

    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
    ي
    -3.00
    </i>
    -2.91
    i
    -2.77
    い
    -2.73
     are
    -2.47
    нении
    -2.36
     weihnachten
    -2.36
     gesagt
    -2.31
    ি
    -2.28
    й
    -2.19
    POSITIVE LOGITS
     bustling
    2.41
    ם
    2.39
     theres
    2.34
    銕
    2.31
     inspiradoras
    2.22
     mayoría
    2.17
    沨
    2.16
    </sup>
    2.16
    ).”
    2.14
    giène
    2.13
    Activations Density 0.005%

    No Known Activations