© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 31763
    Prev
    Next
    INDEX
    Explanations

    irreducible representations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     homot
    0.42
    痔
    0.41
    躓
    0.40
    闶
    0.40
     διο
    0.38
     homotopy
    0.36
     Feedback
    0.36
     Sardinia
    0.36
    羧
    0.36
    ώρα
    0.35
    POSITIVE LOGITS
     irre
    0.63
    irre
    0.54
     irreducible
    0.50
     weight
    0.44
     representation
    0.43
     irrevers
    0.43
     irreparable
    0.43
     highest
    0.42
     inequ
    0.41
     representations
    0.41
    Activations Density 0.003%

    No Known Activations