© 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. 147721
    Prev
    Next
    INDEX
    Explanations

    obese patient, World Bank, bad parts

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

    effects and consequences

    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
    getCql
    0.53
     checkered
    0.53
     exemplifies
    0.48
    са
    0.47
    EndZ
    0.45
    testers
    0.45
    кування
    0.45
    茣
    0.44
     denotes
    0.44
     imperfection
    0.44
    POSITIVE LOGITS
    Jorge
    0.50
    Jose
    0.45
    匪
    0.45
    爱
    0.45
    带
    0.43
    大家
    0.43
    碧
    0.43
    बद्ध
    0.43
     Bila
    0.43
    정
    0.42
    Activations Density 0.001%

    No Known Activations