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
    3. 16-GEMMASCOPE-2-RES-16K
    4. 55
    Prev
    Next
    INDEX
    Explanations

    Distance from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <
    0.58
     शिवाय
    0.57
    op
    0.56
    [
    0.56
    els
    0.55
    ans
    0.55
    endants
    0.51
    ts
    0.48
    v
    0.48
    olt
    0.47
    POSITIVE LOGITS
    LastGen
    0.59
    ው
    0.56
     fenomeni
    0.54
     procesos
    0.53
     ด่า
    0.53
     ജ
    0.53
    网址
    0.53
     Prozesse
    0.52
     Дж
    0.52
    冋
    0.51
    Activations Density 0.000%

    No Known Activations