© 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. 9198
    Prev
    Next
    INDEX
    Explanations

    __typeof version Static kernel

    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
    🫣
    -1.95
    k
    -1.93
     itſelf
    -1.86
     romper
    -1.83
    ers
    -1.81
    咵
    -1.69
    s
    -1.63
     ilegal
    -1.57
    leute
    -1.57
     went
    -1.55
    POSITIVE LOGITS
     the
    2.72
     they
    2.19
     quintessential
    2.05
     nonchal
    1.99
    ,;
    1.98
     нескольких
    1.92
     einige
    1.92
     blossoming
    1.89
     predominantly
    1.88
     famed
    1.88
    Activations Density 0.002%

    No Known Activations