© 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. 45283
    Prev
    Next
    INDEX
    Explanations

    superalgebras

    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
    hanno
    -1.45
    </strong>
    -1.42
     zonder
    -1.38
     tą
    -1.38
     Deze
    -1.36
    否则
    -1.35
     effici
    -1.35
     that
    -1.35
    ꪻ
    -1.34
    andı
    -1.31
    POSITIVE LOGITS
     them
    1.54
     at
    1.53
     in
    1.52
    ումներ
    1.46
    了不少
    1.41
    f
    1.41
    了一些
    1.30
     as
    1.27
     just
    1.25
     using
    1.25
    Activations Density 0.099%

    No Known Activations