© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32657
    Prev
    Next
    INDEX
    Explanations

    experimental and empirical research

    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
    Negative Logits
    ︓
    -1.34
    荭
    -1.33
     både
    -1.32
     tiga
    -1.30
     verschillende
    -1.30
     zowel
    -1.27
     involucra
    -1.24
     podría
    -1.21
     três
    -1.20
    kkor
    -1.19
    POSITIVE LOGITS
     methods
    1.47
     effort
    1.45
     assistance
    1.37
    </em>
    1.36
    $
    1.35
     attempt
    1.33
     efforts
    1.33
     PartialEq
    1.33
     noteworthy
    1.32
     suggestions
    1.30
    Activations Density 0.219%

    No Known Activations