© 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. 53163
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

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

    list formatting and instructions

    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
    скольку
    0.42
     যেহেতু
    0.39
     ಅನುಪ
    0.38
     настолько
    0.38
     일반적으로
    0.38
    若
    0.37
     heretofore
    0.36
    所
    0.36
    DE
    0.36
     Painters
    0.36
    POSITIVE LOGITS
     لكن
    0.54
     แถม
    0.54
    但也
    0.54
     errado
    0.50
     देयर
    0.48
     étape
    0.48
     jangan
    0.48
     แต่
    0.48
     mutta
    0.47
     Jangan
    0.47
    Activations Density 0.028%

    No Known Activations