© 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. 16-GEMMASCOPE-2-RES-262K
    7. 103920
    Prev
    Next
    INDEX
    Explanations

    taskbar

    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_16_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
    ో
    0.64
    스
    0.59
    Type
    0.58
     thiểu
    0.58
     in
    0.58
    ూ
    0.57
    6
    0.56
    
    0.56
    !');
    0.55
     verbind
    0.55
    POSITIVE LOGITS
    agon
    0.61
     récemment
    0.61
    ਾਲ
    0.60
     Για
    0.59
    ри
    0.59
     Кра
    0.57
     Зна
    0.56
    inos
    0.55
     वर
    0.55
    ową
    0.55
    Activations Density 0.001%

    No Known Activations