© 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. 198071
    Prev
    Next
    INDEX
    Explanations

    justification, uniting, use

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

    core concepts and theorems

    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
     እና
    0.51
     電動
    0.51
     עם
    0.50
     पृथ्वी
    0.46
    櫃
    0.45
     Explos
    0.45
     (+
    0.44
     zina
    0.44
    पृथ्वी
    0.44
     並
    0.44
    POSITIVE LOGITS
    িন
    0.51
    ляем
    0.47
     justified
    0.46
     которым
    0.45
    творе
    0.45
     first
    0.45
    ешь
    0.44
    ﻟ
    0.44
     shared
    0.43
    始めた
    0.43
    Activations Density 0.001%

    No Known Activations