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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12380
    Prev
    Next
    INDEX
    Explanations

    state or description

    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
     exceedingly
    0.40
    罍
    0.40
    壃
    0.40
    <unused416>
    0.40
    нести
    0.39
     estremamente
    0.39
    <unused347>
    0.39
     difíciles
    0.39
    <unused374>
    0.39
    <unused639>
    0.39
    POSITIVE LOGITS
     (
    0.53
     或
    0.48
    '
    0.47
     অর্থাৎ
    0.46
    ().
    0.44
     with
    0.44
    y
    0.43
     删除
    0.42
     =
    0.41
     [
    0.41
    Activations Density 0.179%

    No Known Activations