© 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. 75272
    Prev
    Next
    INDEX
    Explanations

    noun followed by descriptor

    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
     on
    -2.19
     to
    -1.96
     you
    -1.92
     from
    -1.88
     we
    -1.85
     by
    -1.82
     for
    -1.81
     as
    -1.63
     There
    -1.62
     with
    -1.59
    POSITIVE LOGITS
     teneb
    1.73
    órica
    1.66
    ‪.‬‬
    1.63
     espr
    1.59
     kazak
    1.59
    穌
    1.59
     dafs
    1.56
    夘
    1.54
    Therefore
    1.53
     sobri
    1.53
    Activations Density 0.152%

    No Known Activations