© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 21666
    Prev
    Next
    INDEX
    Explanations

    actions and body parts

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

    open and smiling

    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
     якщо
    0.59
    銥
    0.55
    埛
    0.53
    堊
    0.53
    瘧
    0.53
    ഫൈ
    0.52
     تحقيق
    0.52
     கூட்டணிய
    0.52
    詮
    0.52
     예측
    0.50
    POSITIVE LOGITS
    lu
    0.60
     leisurely
    0.60
     hurriedly
    0.53
    vo
    0.53
     cheerfully
    0.52
     loung
    0.52
     happily
    0.51
     sullen
    0.51
    flutter
    0.50
     carelessly
    0.49
    Activations Density 0.006%

    No Known Activations