© 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. 73480
    Prev
    Next
    INDEX
    Explanations

    Mario followed by a name

    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
    u
    -3.50
    ,"
    -3.11
     \&
    -3.08
    ?"
    -2.97
    ’
    -2.84
    </em>
    -2.73
    ");
    -2.66
    ",
    -2.64
     \
    -2.63
    /
    -2.61
    POSITIVE LOGITS
    汌
    2.83
    𓋼
    2.80
     voorbeeld
    2.66
     意思
    2.56
     coraz
    2.50
     semble
    2.44
     ajouter
    2.41
    ⌵
    2.38
    屃
    2.36
     whom
    2.33
    Activations Density 0.003%

    No Known Activations