© 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. 34-GEMMASCOPE-RES-131K
    7. 30040
    Prev
    Next
    INDEX
    Explanations

    summary, article, strengths, key

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     three
    -1.63
     two
    -1.62
     from
    -1.58
     one
    -1.57
     five
    -1.56
     ‘‘
    -1.52
     in
    -1.49
     during
    -1.48
     at
    -1.48
     on
    -1.48
    POSITIVE LOGITS
     générer
    1.52
     berücksich
    1.49
     colorear
    1.48
     appeler
    1.43
     envoyer
    1.43
     リボン
    1.40
     sembler
    1.38
     insanely
    1.38
     appliquer
    1.36
     indiquer
    1.35
    Activations Density 0.002%

    No Known Activations