© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59887
    Prev
    Next
    INDEX
    Explanations

    data attributes

    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
    狲
    -2.14
     transfé
    -2.02
     zwanzig
    -1.97
     réalisée
    -1.92
    could
    -1.87
     tă
    -1.80
     suscripción
    -1.78
    1
    -1.77
     Such
    -1.73
     comprenant
    -1.73
    POSITIVE LOGITS
     \
    1.92
     at
    1.88
     offers
    1.74
    اں
    1.70
     confirms
    1.63
     makes
    1.62
     strives
    1.61
     combines
    1.56
     gives
    1.54
    Perhaps
    1.52
    Activations Density 0.011%

    No Known Activations