© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12299
    Prev
    Next
    INDEX
    Explanations

    python imports

    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
     for
    -2.05
     to
    -1.82
     on
    -1.68
     a
    -1.62
     by
    -1.54
     only
    -1.53
    了不少
    -1.52
     through
    -1.51
     at
    -1.48
     out
    -1.47
    POSITIVE LOGITS
     nettoyer
    1.38
    žiť
    1.36
     två
    1.36
     corriger
    1.36
     '^
    1.32
    ↵↵
    1.31
     supprimer
    1.30
     cliquer
    1.30
     recentemente
    1.29
     seleccionar
    1.28
    Activations Density 0.013%

    No Known Activations