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
    3. 16-GEMMASCOPE-2-RES-16K
    4. 177
    Prev
    Next
    INDEX
    Explanations

    paint, nail, stitch

    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
     muffins
    0.71
     :/
    0.70
     alveolar
    0.69
     rectal
    0.68
     pistol
    0.68
     pistols
    0.67
     abduction
    0.67
     femoral
    0.67
    ?”
    0.66
     an
    0.65
    POSITIVE LOGITS
    on
    0.86
    as
    0.84
    to
    0.73
    ل
    0.72
    t
    0.71
    त
    0.70
    总
    0.68
    o
    0.66
    n
    0.66
    عمل
    0.66
    Activations Density 0.062%

    No Known Activations