© 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. 10986
    Prev
    Next
    INDEX
    Explanations

    describing states or possibilities

    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
    moreland
    -1.44
     poten
    -1.39
     Dinas
    -1.36
     imma
    -1.33
     siz
    -1.31
     déroule
    -1.30
     exac
    -1.30
    derdag
    -1.30
     irony
    -1.29
    Ҹ
    -1.29
    POSITIVE LOGITS
     for
    1.55
     just
    1.55
    The
    1.41
     after
    1.41
    .,
    1.38
     Getränke
    1.38
     because
    1.38
     at
    1.35
     versatile
    1.33
    ).
    1.32
    Activations Density 0.072%

    No Known Activations