© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86272
    Prev
    Next
    INDEX
    Explanations

    don't wait

    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
    पुर
    -1.09
    🛢
    -1.07
     siena
    -1.06
    hline
    -1.05
    AYO
    -1.05
     Sélectionnez
    -1.04
    几何
    -1.04
    дио
    -1.04
     accepted
    -1.04
     deze
    -1.04
    POSITIVE LOGITS
     to
    1.91
     by
    1.52
     menegaskan
    1.19
    Trois
    1.18
     however
    1.18
    yarakat
    1.18
    那时候
    1.17
     görmek
    1.16
    gemeente
    1.16
     Whose
    1.16
    Activations Density 0.029%

    No Known Activations