© 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. 64609
    Prev
    Next
    INDEX
    Explanations

    fonts and scripts

    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
    Not in Any Lists

    No Comments

    Negative Logits
     before
    -1.97
     during
    -1.69
     system
    -1.55
     after
    -1.55
     or
    -1.55
     came
    -1.50
     until
    -1.48
     went
    -1.46
     method
    -1.45
     took
    -1.43
    POSITIVE LOGITS
    屨
    1.66
    Spieler
    1.66
    沵
    1.57
     écl
    1.55
     élev
    1.55
    蠵
    1.52
     voyant
    1.49
     maniere
    1.47
     petites
    1.46
    Angebot
    1.46
    Activations Density 0.003%

    No Known Activations