© 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. 22354
    Prev
    Next
    INDEX
    Explanations

    sw prefix

    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
     \
    -3.73
    S
    -2.81
    P
    -2.66
    G
    -2.66
    in
    -2.52
    ものに
    -2.50
    </em>
    -2.47
    al
    -2.45
     innych
    -2.45
     The
    -2.42
    POSITIVE LOGITS
    locene
    2.61
    thouses
    2.61
    ارتمان
    2.55
    輥
    2.48
    tuce
    2.47
    oaks
    2.44
     情侣
    2.44
    ycznych
    2.42
     humeur
    2.42
     şir
    2.33
    Activations Density 0.019%

    No Known Activations