© 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. 89420
    Prev
    Next
    INDEX
    Explanations

    detailed information and specific places

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

    social cues, dialogue, plots

    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
     Grun
    0.47
     வான
    0.46
    וג
    0.45
     milieu
    0.45
    वृत्ति
    0.44
     アップ
    0.43
    互
    0.43
     mull
    0.43
     countably
    0.43
     உங்கள்
    0.42
    POSITIVE LOGITS
    顽
    0.54
    ૩
    0.53
    誂
    0.47
    蕲
    0.46
     निशाना
    0.44
    β
    0.44
     фай
    0.43
     پہلے
    0.43
     unexplored
    0.43
    गमेंट
    0.43
    Activations Density 0.000%

    No Known Activations