© 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. 41908
    Prev
    Next
    INDEX
    Explanations

    computer software and control

    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
     遊ん
    0.57
    GoAbroad
    0.54
     виправивши
    0.52
    ᅦ
    0.50
     благоприят
    0.50
    ᅡ
    0.50
     змен
    0.49
     политика
    0.49
     옳은
    0.48
    ㄆ
    0.48
    POSITIVE LOGITS
     software
    0.97
     computer
    0.93
     computers
    0.87
     computerized
    0.86
     electronic
    0.82
     control
    0.80
     digital
    0.79
     programming
    0.78
     electronics
    0.74
    software
    0.74
    Activations Density 0.125%

    No Known Activations