© 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. 44095
    Prev
    Next
    INDEX
    Explanations

    doi identifier

    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
     the
    -2.73
    ,
    -1.73
     The
    -1.66
    ...........
    -1.65
     underlines
    -1.60
     we
    -1.58
     What
    -1.57
     whatnot
    -1.54
    あっという間に
    -1.51
     Geen
    -1.47
    POSITIVE LOGITS
    但是在
    1.77
     mutta
    1.77
     אבל
    1.74
    </h2>
    1.68
    ércoles
    1.67
     dát
    1.66
    勖
    1.66
     bedre
    1.63
    changers
    1.59
    izoen
    1.57
    Activations Density 0.081%

    No Known Activations