Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12200
    Prev
    Next
    INDEX
    Explanations

    surface of

    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
    и
    0.54
    but
    0.53
    as
    0.53
    at
    0.50
    to
    0.50
    is
    0.49
    ish
    0.49
    that
    0.48
    rule
    0.47
    in
    0.46
    POSITIVE LOGITS
    鮋
    0.44
     ડિ
    0.43
     নগর
    0.42
     Scranton
    0.41
     insects
    0.41
     raids
    0.41
     próprios
    0.41
     Montevideo
    0.40
     डि
    0.40
    させる
    0.40
    Activations Density 0.036%

    No Known Activations