© 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. 22-GEMMASCOPE-RES-131K
    7. 34608
    Prev
    Next
    INDEX
    Explanations

    Jan Op

    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
    時々
    -1.25
     this
    -1.20
    の方に
    -1.12
    感じで
    -1.11
    这家伙
    -1.09
     our
    -1.09
    割と
    -1.08
    で見る
    -1.06
    遠慮
    -1.05
    !
    -1.04
    POSITIVE LOGITS
     instead
    1.33
    が
    1.27
    では
    1.25
    emed
    1.23
    靱
    1.22
    abilia
    1.21
     wasn
    1.20
    despite
    1.19
    Tienen
    1.16
     aparatos
    1.16
    Activations Density 0.001%

    No Known Activations