© 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. 84415
    Prev
    Next
    INDEX
    Explanations

    #include directives and comments

    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
    k
    -2.05
     then
    -1.94
    n
    -1.94
    b
    -1.90
    ,
    -1.88
    m
    -1.84
    de
    -1.73
     eventually
    -1.70
    h
    -1.69
    ne
    -1.67
    POSITIVE LOGITS
    >>(
    1.59
    aVar
    1.59
    dicht
    1.59
    」，
    1.55
    gangss
    1.53
    　　　　　
    1.48
     länder
    1.43
    毖
    1.41
     arşivlendi
    1.41
    thâu
    1.41
    Activations Density 0.075%

    No Known Activations