© 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. 20085
    Prev
    Next
    INDEX
    Explanations

    if or not comparisons

    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
    /
    0.52
    ᔨ
    0.46
    ゝ
    0.44
    -
    0.43
     "../../
    0.42
    哀
    0.39
    大家好
    0.39
    棸
    0.39
    起来
    0.39
    宗
    0.38
    POSITIVE LOGITS
    INCRE
    0.52
    ecek
    0.49
    новых
    0.49
    jego
    0.49
    новый
    0.48
    но
    0.48
    increased
    0.48
    かかる
    0.47
    perm
    0.46
    increases
    0.46
    Activations Density 0.002%

    No Known Activations