© 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. 6773
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming terms

    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
     reason
    -1.73
     espere
    -1.57
     contado
    -1.49
    ሯ
    -1.43
     motivo
    -1.43
    目标
    -1.43
    DISTRIB
    -1.41
    をよく
    -1.38
     recomendado
    -1.37
    几点
    -1.37
    POSITIVE LOGITS
     from
    1.77
     Sejarah
    1.70
     karier
    1.45
    C
    1.45
    Such
    1.45
     Wartawan
    1.40
    Wishing
    1.38
    hline
    1.37
    such
    1.30
     Godt
    1.30
    Activations Density 0.003%

    No Known Activations