© 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. 7041
    Prev
    Next
    INDEX
    Explanations

    asking for clarification

    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
    т
    0.36
    н
    0.34
     وعرف
    0.32
    ،
    0.30
    ਨ
    0.30
    ，
    0.28
    Shortcut
    0.28
    Secondo
    0.27
    worth
    0.27
    ক
    0.27
    POSITIVE LOGITS
     they
    0.46
     you
    0.39
     it
    0.30
     они
    0.30
     we
    0.30
     she
    0.29
     bạn
    0.29
     họ
    0.29
     அவர்கள்
    0.28
     THEY
    0.28
    Activations Density 0.103%

    No Known Activations