© 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. 35011
    Prev
    Next
    INDEX
    Explanations

    replace bracketed information

    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
    弜
    0.51
     Вул
    0.50
     उम्र
    0.49
    Hoist
    0.48
    車種
    0.48
    贩
    0.48
     мате
    0.47
     کیل
    0.46
     سانت
    0.46
    籶
    0.46
    POSITIVE LOGITS
    in
    0.51
     on
    0.51
    at
    0.49
     side
    0.47
     colored
    0.46
     consequences
    0.45
     contrary
    0.44
    on
    0.44
    al
    0.44
     sides
    0.43
    Activations Density 0.001%

    No Known Activations