© 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. 67441
    Prev
    Next
    INDEX
    Explanations

    names and abbreviations

    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
    silueta
    -2.48
    们的
    -2.47
     größte
    -2.45
     vollständige
    -2.44
     famosas
    -2.44
     notre
    -2.41
    嘥
    -2.41
    🡺
    -2.38
    骉
    -2.36
    鈊
    -2.36
    POSITIVE LOGITS
    [
    3.80
    We
    3.73
    When
    3.52
    .
    3.45
    as
    3.25
    While
    3.03
    」
    2.97
    After
    2.86
    in
    2.84
    }$
    2.84
    Activations Density 0.012%

    No Known Activations