© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128768
    Prev
    Next
    INDEX
    Explanations

    long long, unsigned int literals

    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
    h
    -1.88
    ik
    -1.80
    t
    -1.77
    r
    -1.71
    ij
    -1.68
    ka
    -1.67
    v
    -1.66
    are
    -1.63
    u
    -1.60
    p
    -1.57
    POSITIVE LOGITS
     sorgfäl
    1.77
     üblichen
    1.77
    butuhkan
    1.75
     echten
    1.66
     häufigsten
    1.66
     dunklen
    1.56
     freundlichen
    1.55
     grossen
    1.55
    feliz
    1.53
    camisetas
    1.53
    Activations Density 0.000%

    No Known Activations