© 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. 144946
    Prev
    Next
    INDEX
    Explanations

    religious and political figures

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

    diplomatic exchange

    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
    უთ
    0.52
    ంగ్
    0.47
    اردوش
    0.46
     infrastrukt
    0.46
    樁
    0.46
    ཿ
    0.46
    㧣
    0.45
    anik
    0.45
     traditionnelle
    0.45
    ashe
    0.45
    POSITIVE LOGITS
    0.48
     சதவீ
    0.48
     weeks
    0.46
     Russian
    0.46
     salient
    0.46
     leather
    0.46
     weekend
    0.46
     Appendix
    0.45
     consider
    0.45
     came
    0.45
    Activations Density 0.001%

    No Known Activations