© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 140
    Prev
    Next
    INDEX
    Explanations

    all or most followed by number/group

    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
     which
    -1.90
     what
    -1.73
     with
    -1.73
     or
    -1.56
     where
    -1.48
     and
    -1.47
     just
    -1.46
     their
    -1.41
     on
    -1.38
     maybe
    -1.38
    POSITIVE LOGITS
    鸶
    1.63
     gouttes
    1.48
     toutefois
    1.30
     diminuer
    1.29
     oublier
    1.29
     tejto
    1.28
    ひら
    1.28
     sembler
    1.24
    屁股
    1.24
     ajouter
    1.24
    Activations Density 0.052%

    No Known Activations