© 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. 71951
    Prev
    Next
    INDEX
    Explanations

    attribute names or identifiers

    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
     "..\..\..\
    -1.67
    如
    -1.65
     solides
    -1.65
     olie
    -1.59
     industrie
    -1.55
     traditionelle
    -1.53
     appels
    -1.51
     دیجیتال
    -1.50
     professionelle
    -1.50
     från
    -1.48
    POSITIVE LOGITS
     which
    2.11
    لبية
    1.84
     as
    1.78
     just
    1.64
     different
    1.63
     enormously
    1.58
     touted
    1.57
    </h3>
    1.55
    leggio
    1.54
    adjective
    1.52
    Activations Density 0.068%

    No Known Activations