© 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. 68375
    Prev
    Next
    INDEX
    Explanations

    fist and fistula

    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
    Not in Any Lists

    No Comments

    Negative Logits
     –
    -3.25
    The
    -3.06
    <i>
    -3.02
    0
    -2.95
    ve
    -2.91
    H
    -2.84
    </td>
    -2.56
    殽
    -2.56
    T
    -2.55
    U
    -2.55
    POSITIVE LOGITS
    ઞ
    2.83
    𓆸
    2.80
     він
    2.73
    arynx
    2.70
    ৢ
    2.66
    眙
    2.55
    
    2.50
    ዡ
    2.45
    imantan
    2.44
     reeling
    2.44
    Activations Density 0.003%

    No Known Activations