© 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. 22-GEMMASCOPE-RES-131K
    7. 16019
    Prev
    Next
    INDEX
    Explanations

    go code and Authors

    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_22/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
    you
    -3.56
    m
    -3.20
    t
    -3.20
    when
    -3.13
    re
    -3.08
    what
    -3.02
    </b>
    -2.78
    which
    -2.73
    de
    -2.63
    man
    -2.63
    POSITIVE LOGITS
     Our
    2.69
     legions
    2.58
    ⟣
    2.38
     asamblea
    2.36
     infuriating
    2.34
     terá
    2.30
    ichteten
    2.25
    ↵
    2.23
    𖣘
    2.23
     tendrá
    2.19
    Activations Density 0.037%

    No Known Activations