© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60327
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
     for
    -2.25
    了一会儿
    -1.84
    *
    -1.59
    ANTED
    -1.55
     серый
    -1.53
    You
    -1.52
    了好
    -1.52
    ;
    -1.49
     stycznia
    -1.48
    meester
    -1.48
    POSITIVE LOGITS
     EACH
    1.78
     they
    1.77
     the
    1.77
     rempliss
    1.67
     první
    1.63
     it
    1.54
     absolut
    1.52
     komfor
    1.50
    ㍉
    1.48
    Variante
    1.47
    Activations Density 0.015%

    No Known Activations