© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72104
    Prev
    Next
    INDEX
    Explanations

    sino-, 而且, а, rather, /*, Thursday, Product, A, Q

    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
    Negative Logits
     of
    -2.97
    퐹
    -2.73
    s
    -2.66
    hamilan
    -2.41
    antaranya
    -2.25
    //
    -2.11
    harapkan
    -2.09
    вала
    -2.06
    libatkan
    -1.99
    さんも
    -1.95
    POSITIVE LOGITS
     —
    2.59
    </em>
    2.47
    鋱
    2.31
     και
    2.19
     mesmos
    2.19
     этапе
    2.16
    "
    2.16
    鹪
    2.14
    鸸
    2.13
    鹀
    2.11
    Activations Density 0.000%

    No Known Activations