© 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. 32887
    Prev
    Next
    INDEX
    Explanations

    file operations: write/save

    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
    neither
    0.37
    mayın
    0.37
    
    0.37
     Dancer
    0.36
    hæng
    0.35
     जुगा
    0.35
     юк
    0.35
     treści
    0.34
    曖
    0.34
    Neither
    0.34
    POSITIVE LOGITS
     saving
    0.63
     save
    0.62
     Save
    0.58
     saves
    0.58
    保存
    0.56
    save
    0.55
     SAVE
    0.55
    Save
    0.55
     保存
    0.54
    导出
    0.54
    Activations Density 0.168%

    No Known Activations