© 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. 108062
    Prev
    Next
    INDEX
    Explanations

    immediately obvious

    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
    0.46
     ed
    0.41
     quatern
    0.40
    شون
    0.40
    \
    0.40
    هم
    0.39
     conclu
    0.39
    ...
    0.39
    begin
    0.38
     imperfect
    0.38
    POSITIVE LOGITS
    𝘩
    0.52
     расходов
    0.49
    at
    0.47
     ढु
    0.46
    ੇ
    0.46
    的相关
    0.46
     மாநக
    0.45
     Recipes
    0.44
    ifting
    0.44
     अथवा
    0.44
    Activations Density 0.002%

    No Known Activations