© 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. 31-GEMMASCOPE-2-RES-262K
    7. 138971
    Prev
    Next
    INDEX
    Explanations

    systems reaching equilibrium or acting on desires

    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_31_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
    essere
    0.49
    fee
    0.43
    '
    0.43
    Dance
    0.42
    inas
    0.41
    este
    0.41
    asang
    0.40
    eep
    0.40
    arena
    0.40
    elipe
    0.39
    POSITIVE LOGITS
    㜌
    0.56
    쩍
    0.52
     transact
    0.50
    ඃ
    0.49
     cockpit
    0.47
     knowledgeable
    0.45
     bekannten
    0.45
     warrant
    0.45
     معروف
    0.44
     фаразы
    0.43
    Activations Density 0.003%

    No Known Activations