© 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. 100941
    Prev
    Next
    INDEX
    Explanations

    programming and technical contexts

    np_acts-logits-general · gemini-2.5-flash-lite

    word fragments in non-English text, particularly Slavic languages like Russian, Czech, and Slovak.

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @bfgcn7frf5
    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
    ’
    -2.13
    So
    -1.66
    Our
    -1.63
     trabajar
    -1.52
     dispuestos
    -1.43
     Begründung
    -1.43
     he
    -1.42
     to
    -1.40
    になるので
    -1.40
     be
    -1.38
    POSITIVE LOGITS
     zodiaco
    1.72
     Houſe
    1.66
    piecze
    1.59
     präsenti
    1.55
     verfügen
    1.54
     rosario
    1.54
     are
    1.52
    面白
    1.49
     fraîche
    1.47
     inade
    1.46
    Activations Density 0.004%

    No Known Activations