© 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. 17633
    Prev
    Next
    INDEX
    Explanations

    instead, clarification, or alternative

    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
     Европа
    0.47
    ITTER
    0.47
    Ⅹ
    0.46
    ా
    0.45
    Europe
    0.45
    년부터
    0.44
    Anomaly
    0.43
    damageCount
    0.43
     الخير
    0.43
    UIActions
    0.43
    POSITIVE LOGITS
     friction
    0.53
     zeta
    0.50
     pela
    0.48
    મ
    0.48
    د
    0.47
     accretion
    0.47
     speedy
    0.47
     traction
    0.44
     works
    0.44
     cones
    0.44
    Activations Density 0.002%

    No Known Activations