© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 41660
    Prev
    Next
    INDEX
    Explanations

    Forced proximity

    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
    凵
    0.59
     ўз
    0.55
    𒃻
    0.50
     ನೆಲಮಾಳಿಗೆ
    0.48
    góc
    0.47
    ଷ
    0.47
     মেয়ে
    0.46
    高等学校
    0.46
     πάνω
    0.46
     बैचलर्स
    0.45
    POSITIVE LOGITS
     
    0.66
    i
    0.45
    http
    0.45
    hens
    0.43
    We
    0.43
     proje
    0.42
    util
    0.41
    Stay
    0.41
    jQuery
    0.41
    C
    0.40
    Activations Density 0.003%

    No Known Activations