© 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. 68016
    Prev
    Next
    INDEX
    Explanations

    overload and override methods

    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
    有个
    -1.38
     récord
    -1.37
    踯
    -1.31
     fêtes
    -1.28
     wyja
    -1.23
    ﾖ
    -1.21
     mejora
    -1.21
     pequeno
    -1.20
     fortalec
    -1.20
     mejorar
    -1.19
    POSITIVE LOGITS
    </sup>
    1.58
     to
    1.52
    s
    1.19
    v
    1.17
     با
    1.17
    MIDDLEWARE
    1.14
     –
    1.13
     Moreover
    1.12
     burdensome
    1.12
    є
    1.10
    Activations Density 0.057%

    No Known Activations