© 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. 73535
    Prev
    Next
    INDEX
    Explanations

    integer ring notation subscripts

    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
    E
    -1.67
    𓍊
    -1.64
     dziś
    -1.53
     that
    -1.45
     perdidos
    -1.43
     aislados
    -1.37
     Using
    -1.34
     should
    -1.34
     

    -1.34
    节省
    -1.34
    POSITIVE LOGITS
    ,
    1.49
    得
    1.41
    Ᏺ
    1.37
    ཪ
    1.36
    Sinopse
    1.36
    owę
    1.31
    enses
    1.31
    )$,
    1.29
    PLANE
    1.29
     dissi
    1.26
    Activations Density 0.018%

    No Known Activations