© 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. 70798
    Prev
    Next
    INDEX
    Explanations

    stitching numbers

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

    document polishing traced sketching measured

    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
     Localization
    0.47
    ൈ
    0.45
     localization
    0.45
    Localization
    0.44
    を確認
    0.44
    ردم
    0.42
    ഥി
    0.41
     tril
    0.41
     Fahrt
    0.41
    ization
    0.40
    POSITIVE LOGITS
     предотвра
    0.50
     我的
    0.49
    餐
    0.48
     outraged
    0.48
     моей
    0.48
    =\
    0.47
    🍝
    0.46
     ин
    0.46
    购物车
    0.45
    我的
    0.45
    Activations Density 0.001%

    No Known Activations