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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12346
    Prev
    Next
    INDEX
    Explanations

    foreign language text fragments

    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
    fordshire
    -1.45
     XXXVII
    -1.43
     folgenden
    -1.40
    但却
    -1.40
     spind
    -1.37
     jenem
    -1.36
    usi
    -1.35
    strator
    -1.35
     resid
    -1.34
    '';
    -1.34
    POSITIVE LOGITS
     items
    1.61
    kursi
    1.58
    telah
    1.54
     cafetería
    1.52
     warszawa
    1.48
    mdan
    1.48
     all
    1.45
    rozum
    1.41
    őség
    1.41
     one
    1.40
    Activations Density 0.004%

    No Known Activations