© 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. 10523
    Prev
    Next
    INDEX
    Explanations

    events in time or history

    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
     with
    -3.02
     our
    -2.64
     those
    -2.47
     without
    -2.39
     as
    -2.16
     before
    -2.16
     using
    -2.08
     all
    -2.08
     from
    -2.05
     only
    -2.02
    POSITIVE LOGITS
     parlent
    1.89
     maniere
    1.88
     lavable
    1.84
     unbelievably
    1.79
    が無い
    1.75
     ondu
    1.75
     rêver
    1.74
     promove
    1.72
     AMAZING
    1.69
     deviennent
    1.68
    Activations Density 0.393%

    No Known Activations