© 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. 13576
    Prev
    Next
    INDEX
    Explanations

    select, bypassing, determinism, LinkedIn post

    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
    ady
    0.48
    ptosis
    0.45
    down
    0.45
    c
    0.45
    k
    0.43
    थो
    0.43
    rishna
    0.43
    kada
    0.43
    iliary
    0.42
    dead
    0.41
    POSITIVE LOGITS
    篇
    0.48
     Бы
    0.46
    ွာ
    0.46
     mia
    0.45
    我的
    0.44
    我是
    0.44
    邡
    0.44
     minha
    0.43
     popolazione
    0.43
     miei
    0.42
    Activations Density 0.009%

    No Known Activations