© 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. 138744
    Prev
    Next
    INDEX
    Explanations

    differences, Regulation, detection

    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
    鴟
    0.57
    Კ
    0.56
    
    0.56
    𝘆
    0.55
    arında
    0.54
    敺
    0.53
     doppio
    0.53
    伷
    0.53
     retShape
    0.52
    나요
    0.50
    POSITIVE LOGITS
     Orwell
    0.50
    ,
    0.46
    gee
    0.45
    und
    0.43
    unn
    0.42
    implies
    0.42
    ooi
    0.40
    obo
    0.39
    $,
    0.38
    obviously
    0.38
    Activations Density 0.000%

    No Known Activations