© 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. 16968
    Prev
    Next
    INDEX
    Explanations

    text editor

    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
    იღ
    0.47
    變成
    0.46
    মিটার
    0.46
     pavilion
    0.46
     सो
    0.45
     restaurant
    0.44
    蛞
    0.44
    aking
    0.44
     ඔහුගේ
    0.44
     หา
    0.44
    POSITIVE LOGITS
    اد
    0.45
     vru
    0.44
    দূর
    0.43
     gelegen
    0.43
    ン
    0.42
     volumes
    0.41
    جلات
    0.41
    ادية
    0.40
    ミックス
    0.40
    ল
    0.40
    Activations Density 0.001%

    No Known Activations