© 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. 85558
    Prev
    Next
    INDEX
    Explanations

    namespace identifiers

    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
    :
    -2.47
     by
    -2.27
     their
    -1.99
     as
    -1.98
     on
    -1.97
     one
    -1.90
     are
    -1.80
     from
    -1.75
    There
    -1.73
     will
    -1.70
    POSITIVE LOGITS
    螣
    1.73
     PUSTAKA
    1.73
    峮
    1.63
     美しい
    1.61
     ,‬
    1.59
    缡
    1.59
    jeuner
    1.56
    憷
    1.55
    `)
    1.55
    aning
    1.54
    Activations Density 0.000%

    No Known Activations