© 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. 193935
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific contexts

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

    breaking down and building up

    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
     violators
    0.46
    钊
    0.46
     bearers
    0.46
    ق
    0.46
    ወቅ
    0.45
    ಬ
    0.44
    গিরই
    0.44
     бў
    0.44
    менять
    0.44
     claves
    0.44
    POSITIVE LOGITS
     বুলেট
    0.49
     ARRAY
    0.48
    !=
    0.44
    ㅋㅋㅋㅋㅋㅋㅋㅋ
    0.41
    
    0.41
    ंटी
    0.40
     STRUCTURE
    0.40
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.40
     "<<
    0.40
    ﻋ
    0.40
    Activations Density 0.001%

    No Known Activations