© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 85167
    Prev
    Next
    INDEX
    Explanations

    locations, time periods, or roles

    np_acts-logits-general · gemini-2.5-flash-lite

    overly dramatic or sensational openings

    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_31_width_262k_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
     sprouting
    0.58
    len
    0.52
    hoot
    0.49
    as
    0.49
     sprinkles
    0.49
    s
    0.47
     substantial
    0.46
     bouncy
    0.46
    的其他
    0.46
     sprout
    0.45
    POSITIVE LOGITS
    สัญญาณ
    0.50
    湎
    0.49
    วี
    0.48
     годы
    0.48
    ﺩ
    0.47
     લઈ
    0.46
     अमृतसर
    0.46
    手表
    0.46
    เข้า
    0.45
    กับ
    0.45
    Activations Density 0.001%

    No Known Activations