© 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. 28691
    Prev
    Next
    INDEX
    Explanations

    examples, troubling, illegal, confidence, likely, vital

    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
    راحی
    0.48
     ergodic
    0.44
    ancellor
    0.44
    h
    0.42
    णाची
    0.41
     Restaurant
    0.40
     Integration
    0.40
    ера
    0.40
     Calculation
    0.39
    یرو
    0.39
    POSITIVE LOGITS
    ");
    0.48
     lasci
    0.45
    
    0.44
    뺑
    0.42
    >();
    0.42
    മല്ല
    0.41
     вмі
    0.41
     実
    0.40
    胴
    0.40
     グレー
    0.40
    Activations Density 0.000%

    No Known Activations