© 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. 113450
    Prev
    Next
    INDEX
    Explanations

    minimize waste

    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
     키
    0.46
    Font
    0.44
    FON
    0.44
     트
    0.43
     ⓒ
    0.43
     Professor
    0.42
    ｩ
    0.42
    f
    0.41
     ট
    0.41
     المت
    0.41
    POSITIVE LOGITS
    ровано
    0.46
    契約
    0.45
    สัญญา
    0.44
     módulos
    0.42
    पूजा
    0.42
    म्मेदारी
    0.41
    なり
    0.41
    鱧
    0.41
    תה
    0.40
    ₡
    0.40
    Activations Density 0.002%

    No Known Activations