© 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. 901
    Prev
    Next
    INDEX
    Explanations

    opening files

    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
     with
    -2.03
     of
    -1.97
     also
    -1.78
     find
    -1.75
     will
    -1.73
    estão
    -1.63
     using
    -1.63
     by
    -1.63
     just
    -1.60
     through
    -1.55
    POSITIVE LOGITS
     stirs
    1.66
     asserts
    1.65
     quinze
    1.61
     podría
    1.59
    customized
    1.59
    他们是
    1.58
     algodão
    1.56
    胸口
    1.55
    摇了摇头
    1.54
     Excelente
    1.54
    Activations Density 0.002%

    No Known Activations