© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28424
    Prev
    Next
    INDEX
    Explanations

    static method declarations

    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
     different
    -1.31
     all
    -1.19
     from
    -1.18
    []=$
    -1.15
     for
    -1.14
     even
    -1.13
     also
    -1.10
     in
    -1.07
     même
    -1.04
     when
    -1.03
    POSITIVE LOGITS
    わん
    1.09
     pupa
    1.08
     coûts
    1.07
    Etape
    1.05
    Elisa
    1.05
     citar
    1.03
    arthed
    1.01
     duração
    1.01
    いいのか
    1.00
     montagne
    0.99
    Activations Density 0.007%

    No Known Activations