© 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. 85684
    Prev
    Next
    INDEX
    Explanations

    legal pertaining, arriving, caused by

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

    Shibuya crossing

    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
    Negative Logits
     slalom
    0.49
    
    0.48
    ্রিয়া
    0.46
     ्
    0.46
    κο
    0.46
     Cindy
    0.45
    μαν
    0.44
     Debbie
    0.44
     MHD
    0.44
    inizio
    0.44
    POSITIVE LOGITS
     módulos
    0.47
     effectually
    0.46
    НИ
    0.45
    ários
    0.44
    悟空
    0.43
     systematically
    0.43
    ních
    0.42
    ást
    0.42
    繁
    0.42
     vassals
    0.42
    Activations Density 0.000%

    No Known Activations