© 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. 83778
    Prev
    Next
    INDEX
    Explanations

    after "before"

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

    harmful or illegal topics

    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
    !
    0.49
     ktoś
    0.47
     från
    0.46
     wygląda
    0.46
     utilized
    0.44
     blew
    0.44
     D
    0.44
     Lippincott
    0.44
    .~
    0.44
     upgraded
    0.44
    POSITIVE LOGITS
    үз
    0.44
    陖
    0.44
    ServiceImpl
    0.44
    鳧
    0.44
    ૈય
    0.44
     сми
    0.43
    ⅳ
    0.43
     గౌ
    0.43
    ऊस
    0.43
    itiba
    0.43
    Activations Density 0.002%

    No Known Activations