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. 62
    Prev
    Next
    INDEX
    Explanations

    gather data

    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
    <0x0D>
    0.59
    大家
    0.52
    y
    0.51
    o
    0.50
    sidenav
    0.49
     किसे
    0.49
    哪里
    0.48
    subscribe
    0.48
    applicable
    0.48
    เยอะ
    0.48
    POSITIVE LOGITS
    ل
    0.73
     ມີ
    0.61
     그는
    0.57
     bimodule
    0.57
     bombardment
    0.56
    ാ
    0.56
     seines
    0.55
    मा
    0.55
    ע
    0.54
     singularity
    0.53
    Activations Density 0.001%

    No Known Activations