© 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-16K
    7. 579
    Prev
    Next
    INDEX
    Explanations

    introducing a concept

    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_16k_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
    ’
    0.41
    /
    0.39
    et
    0.35
     (
    0.34
    on
    0.33
    ation
    0.33
     Rc
    0.32
    inerary
    0.32
    ir
    0.31
    ified
    0.30
    POSITIVE LOGITS
     విధంగా
    0.41
    Фа
    0.37
     ነው
    0.36
    ра
    0.36
    騁
    0.36
     konuda
    0.35
    רי
    0.35
     분야
    0.34
     ലേഖ
    0.34
     is
    0.34
    Activations Density 0.844%

    No Known Activations