© 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. 22-GEMMASCOPE-RES-131K
    7. 25051
    Prev
    Next
    INDEX
    Explanations

    proper nouns following certain 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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     their
    -2.34
     most
    -2.22
     in
    -2.19
     from
    -2.11
     it
    -1.95
     because
    -1.86
     many
    -1.85
     both
    -1.79
     an
    -1.71
     or
    -1.70
    POSITIVE LOGITS
     stalwart
    1.63
    somewhat
    1.55
     ativar
    1.52
     verhind
    1.51
     Dinas
    1.48
    你不要
    1.48
    ܆
    1.43
     specif
    1.42
    Grazie
    1.41
     deliciously
    1.41
    Activations Density 0.002%

    No Known Activations