© 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. 11481
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific notation

    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
    cisive
    -0.85
     ведь
    -0.84
    partement
    -0.82
    ｷ
    -0.82
     oublié
    -0.81
    حث
    -0.81
    junctive
    -0.79
    bisk
    -0.79
      (
    -0.79
    kHz
    -0.79
    POSITIVE LOGITS
    を持ち
    0.95
    遭受
    0.88
     インスタ
    0.85
     ENO
    0.84
     torino
    0.83
    יותר
    0.83
    墟
    0.81
    oczes
    0.79
     EXERCISE
    0.79
    hosting
    0.79
    Activations Density 0.011%

    No Known Activations