© 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. 103386
    Prev
    Next
    INDEX
    Explanations

    of location

    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
    厛
    -2.42
    apparently
    -1.81
    轳
    -1.80
    showed
    -1.77
     ส์
    -1.75
    が違う
    -1.73
     encantador
    -1.71
     constituer
    -1.67
     hva
    -1.66
    brought
    -1.65
    POSITIVE LOGITS
     of
    3.17
     at
    1.91
     will
    1.86
     on
    1.82
     While
    1.80
    B
    1.72
     should
    1.66
     then
    1.64
     Although
    1.63
     would
    1.62
    Activations Density 0.023%

    No Known Activations