© 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. 9713
    Prev
    Next
    INDEX
    Explanations

    key information and logic

    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
    调用
    0.35
     调用
    0.35
    두
    0.34
    きて
    0.34
    duk
    0.33
    uttosto
    0.32
    StringUtils
    0.32
     ()=>
    0.32
    łek
    0.32
     awkward
    0.32
    POSITIVE LOGITS
     جميع
    0.37
     كافة
    0.34
     بیشتری
    0.34
    だけでなく
    0.33
     wszystkich
    0.32
     علاوه
    0.32
     زيادة
    0.32
     أكثر
    0.32
     الأكثر
    0.31
     بیش
    0.31
    Activations Density 0.111%

    No Known Activations