© 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. 220179
    Prev
    Next
    INDEX
    Explanations

    legal, military, and technical professions

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

    Python code errors

    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
    公园
    0.48
    可在
    0.46
    麿
    0.46
    可以选择
    0.45
    离
    0.45
    可以通过
    0.45
    여기
    0.45
    ه
    0.45
    级的
    0.44
    είς
    0.44
    POSITIVE LOGITS
     detay
    0.51
     continuation
    0.51
     squamous
    0.51
     dri
    0.48
    }{$\
    0.48
     perished
    0.47
    துவாக
    0.47
    ्वती
    0.47
     ener
    0.46
     testi
    0.46
    Activations Density 0.000%

    No Known Activations