© 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. 153955
    Prev
    Next
    INDEX
    Explanations

    governed by laws

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

    Starting and managing specific items or states

    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
    的孩子
    0.52
    '],
    0.50
    ücklich
    0.50
    傣
    0.48
    ']).
    0.46
    傈
    0.46
    ✘
    0.45
    成都
    0.44
    ่าย
    0.44
    ों
    0.44
    POSITIVE LOGITS
     gadgets
    0.57
     or
    0.55
     at
    0.54
     bars
    0.52
     regimens
    0.51
     as
    0.50
     regimen
    0.50
     chances
    0.48
     winnings
    0.48
     millions
    0.47
    Activations Density 0.000%

    No Known Activations