© 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. 281
    Prev
    Next
    INDEX
    Explanations

    programmatic elements, lists, and non-English words

    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
    ,
    -2.48
     some
    -2.33
     of
    -2.23
     where
    -2.03
    /
    -1.96
     our
    -1.85
     these
    -1.81
     on
    -1.73
     Some
    -1.71
    These
    -1.66
    POSITIVE LOGITS
    긔
    2.36
     první
    2.09
    atized
    1.98
     ofta
    1.95
    atization
    1.95
    </tr>
    1.92
     DOMINGO
    1.92
    illir
    1.86
    lograph
    1.86
    ;</
    1.84
    Activations Density 0.056%

    No Known Activations