© 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. 75815
    Prev
    Next
    INDEX
    Explanations

    approach as

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

    exploring or demonstrating positive outcomes

    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
     evit
    0.52
     turpis
    0.51
     ჩატი
    0.51
     permitem
    0.50
     општи
    0.49
    ﻟ
    0.48
    اويه
    0.48
     грун
    0.47
     بتاريخ
    0.46
     enfrent
    0.46
    POSITIVE LOGITS
    ETIME
    0.43
     souffle
    0.43
    装饰
    0.41
    证据
    0.41
     SOI
    0.41
    ⸩
    0.40
    ↵↵
    0.39
     compatibility
    0.39
     positivity
    0.39
     decoration
    0.38
    Activations Density 0.000%

    No Known Activations