© 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. 139118
    Prev
    Next
    INDEX
    Explanations

    wall clock, commercial, Sunday

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

    phrases with symbols or punctuation

    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
    ב
    0.51
    قليم
    0.50
    Від
    0.50
    Т
    0.49
    ف
    0.49
     ترلاسه
    0.49
    การ
    0.48
    Engl
    0.48
    弜
    0.48
    мпания
    0.47
    POSITIVE LOGITS
    pset
    0.54
    atgu
    0.52
    ilit
    0.52
    plist
    0.52
    uff
    0.49
    pytest
    0.47
    keys
    0.46
    passwd
    0.46
    atypes
    0.45
    tab
    0.45
    Activations Density 0.001%

    No Known Activations