© 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. 128524
    Prev
    Next
    INDEX
    Explanations

    photo attributions

    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
     bep
    -1.69
    ⃰
    -1.68
    蟊
    -1.63
     are
    -1.59
     befre
    -1.56
     hef
    -1.56
     certamente
    -1.54
    aimeJ
    -1.54
     permettent
    -1.51
     quieren
    -1.51
    POSITIVE LOGITS
    Not
    2.03
    Some
    1.90
    Once
    1.84
     by
    1.77
    By
    1.75
     with
    1.74
    Very
    1.73
    Through
    1.73
    Like
    1.73
     from
    1.73
    Activations Density 0.027%

    No Known Activations