© 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. 71065
    Prev
    Next
    INDEX
    Explanations

    data labels and 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
    اااا
    -1.07
     participe
    -1.05
    شخص
    -0.95
     alberga
    -0.94
     新款
    -0.93
    jà
    -0.93
     Clase
    -0.93
    ène
    -0.93
    uo
    -0.91
    putAll
    -0.91
    POSITIVE LOGITS
     when
    1.32
    ⽣
    1.25
     and
    1.23
     tazas
    1.19
     that
    1.19
     cuando
    1.18
     with
    1.17
     cuchar
    1.16
    cursions
    1.15
    1.14
    Activations Density 0.028%

    No Known Activations