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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 123580
    Prev
    Next
    INDEX
    Explanations

    HLA type, Damon, Honolulu, Commodore

    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
    してます
    -3.02
     unruly
    -2.98
    撓
    -2.88
     sassy
    -2.83
     crap
    -2.75
     people
    -2.73
     dizzy
    -2.63
     schützen
    -2.61
     führen
    -2.61
     FOR
    -2.61
    POSITIVE LOGITS
    '
    4.66
     heo
    2.98
     inox
    2.98
     hecta
    2.81
    鱚
    2.80
     FRUIT
    2.75
     yf
    2.72
     FISHING
    2.70
     MICHAEL
    2.69
    枼
    2.69
    Activations Density 0.005%

    No Known Activations