© 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. 40-GEMMASCOPE-2-RES-262K
    7. 779
    Prev
    Next
    INDEX
    Explanations

    find mathematical quantities

    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_40_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
    设立
    0.35
    的には
    0.34
    كنولوجيا
    0.33
    <unused45>
    0.33
    hehi
    0.33
    选择了
    0.33
    स्पून
    0.33
    騇
    0.33
    recyclerView
    0.33
     экспери
    0.32
    POSITIVE LOGITS
     approximate
    0.62
     missing
    0.61
     number
    0.55
     smallest
    0.55
     largest
    0.54
     probable
    0.52
    Missing
    0.49
    missing
    0.49
     exact
    0.47
     Approximate
    0.47
    Activations Density 0.016%

    No Known Activations