© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9707
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by capitalized word

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

    list separators, code structures

    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_40_width_16k_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
    2
    0.73
    ج
    0.71
    פ
    0.71
    "
    0.70
    ik
    0.68
    ف
    0.68
    :
    0.67
     be
    0.66
    も
    0.65
    CC
    0.64
    POSITIVE LOGITS
    τή
    0.61
    isinde
    0.60
     І
    0.58
    тно
    0.57
    0.57
    ﺖ
    0.57
    ﺰ
    0.55
    ່ວນ
    0.55
     a
    0.54
    ﻮ
    0.53
    Activations Density 1.558%

    No Known Activations