© 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-65K
    7. 11065
    Prev
    Next
    INDEX
    Explanations

    place or brand followed by subject

    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_65k_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
    写法
    0.40
    ța
    0.35
    ifte
    0.35
    щини
    0.35
     නිර්
    0.34
    <0x0D>
    0.34
    对象
    0.34
     பெற்றது
    0.34
    ﹉
    0.34
    chai
    0.33
    POSITIVE LOGITS
    AL
    0.43
    US
    0.39
    ГО
    0.39
     ಬಹಳ
    0.37
    IS
    0.37
    알
    0.37
    後面
    0.36
     afternoons
    0.36
    AN
    0.36
     ה
    0.35
    Activations Density 0.004%

    No Known Activations