© 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. 25137
    Prev
    Next
    INDEX
    Explanations

    examples after specific nouns

    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
     also
    -1.42
     different
    -1.27
     then
    -1.21
     will
    -1.17
     wanted
    -1.08
     others
    -1.07
    也要
    -1.06
     distintas
    -1.05
     similar
    -1.01
    也有
    -0.98
    POSITIVE LOGITS
     which
    1.62
     that
    1.29
     wherein
    1.12
    jangan
    1.05
    minator
    1.05
     where
    1.04
    🐍
    1.02
    cessed
    1.00
    着的
    0.99
     που
    0.98
    Activations Density 0.064%

    No Known Activations