© 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. 100764
    Prev
    Next
    INDEX
    Explanations

    Commodore, visceral, numerator/denominator

    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
    ￪
    -2.83
     disposent
    -2.75
    ꦺ
    -2.63
     desertcart
    -2.58
    dzić
    -2.58
    廡
    -2.55
     unſ
    -2.53
    ⼥
    -2.53
     feminino
    -2.48
    蹣
    -2.48
    POSITIVE LOGITS
    8
    3.69
    \
    3.30
    X
    2.97
    3
    2.94
    B
    2.91
    2
    2.88
    H
    2.84
    K
    2.77
    on
    2.72
     {
    2.72
    Activations Density 0.026%

    No Known Activations