© 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. 72138
    Prev
    Next
    INDEX
    Explanations

    call, answer, attend, field

    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
    on
    -1.88
    <em>
    -1.85
    ↵
    -1.85
    f
    -1.85
    ya
    -1.71
    *
    -1.70
    d
    -1.68
    as
    -1.68
    ma
    -1.52
     for
    -1.49
    POSITIVE LOGITS
    "));
    1.70
    ๕
    1.63
    </h5>
    1.59
    毎回
    1.55
     椅
    1.55
     Atención
    1.55
    驀
    1.54
    didSet
    1.52
    </i>
    1.48
     dAtA
    1.47
    Activations Density 0.044%

    No Known Activations