© 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. 10-GEMMASCOPE-RES-131K
    7. 38466
    Prev
    Next
    INDEX
    Explanations

    key aspect

    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
    Negative Logits
    ⸨
    -2.08
    
    -1.98
    ᯾
    -1.85
    蚡
    -1.73
    娉
    -1.73
    虓
    -1.69
    ients
    -1.69
    
    -1.61
    歺
    -1.61
    ᥀
    -1.59
    POSITIVE LOGITS
    in
    1.97
    </b>
    1.88
    re
    1.85
     in
    1.61
    which
    1.60
    or
    1.55
    am
    1.52
    一旁
    1.49
     I
    1.48
    up
    1.48
    Activations Density 0.017%

    No Known Activations