© 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. 126501
    Prev
    Next
    INDEX
    Explanations

    reports, lists, catalog

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

    create a business

    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
    Hi
    0.50
    н
    0.49
    King
    0.48
    lowest
    0.48
    Lunch
    0.46
     lowest
    0.45
    ج
    0.45
    Lowest
    0.45
    ש
    0.44
    জ
    0.44
    POSITIVE LOGITS
    umim
    0.57
     문
    0.51
     엘
    0.50
     뮤
    0.49
    oucí
    0.47
    portál
    0.46
     այդ
    0.46
     தெய்வ
    0.45
    纹
    0.45
     ወቅ
    0.45
    Activations Density 0.000%

    No Known Activations