© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 2406
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Linguistics
    0.69
     Psychology
    0.65
    <unused453>
    0.63
     aristocratic
    0.63
     Pharmacology
    0.61
     식품
    0.61
    ાઇન
    0.61
     Coaching
    0.61
    <unused143>
    0.60
     Psychologist
    0.60
    POSITIVE LOGITS
    _
    0.47
      
    0.46
    self
    0.45
    (
    0.42
    Math
    0.42
    ((
    0.40
    ↵
    0.40
    0.40
    new
    0.40
    String
    0.38
    Activations Density 0.780%

    No Known Activations