© 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. 40090
    Prev
    Next
    INDEX
    Explanations

    first to market

    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
    وجوان
    0.52
     көр
    0.50
    iencia
    0.49
    adə
    0.49
    ۥ
    0.48
     Bourg
    0.47
     कपकेक
    0.46
    Crown
    0.46
     सीक्व
    0.46
     instytuc
    0.46
    POSITIVE LOGITS
     of
    0.54
     F
    0.50
     T
    0.49
     mentioned
    0.48
     is
    0.47
     there
    0.47
     et
    0.47
    aches
    0.45
    '
    0.45
     be
    0.44
    Activations Density 0.003%

    No Known Activations