© 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. 184119
    Prev
    Next
    INDEX
    Explanations

    reflexive pronouns

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

    calculating time constraints and scams

    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
     alteration
    0.50
    );
    0.48
    (
    0.47
    of
    0.47
     optimism
    0.45
     quiescent
    0.44
     ischemic
    0.44
    ']]
    0.44
     carcinogenesis
    0.44
    ness
    0.43
    POSITIVE LOGITS
    賏
    0.61
    กำลัง
    0.50
     หย
    0.50
     ইউনিট
    0.49
     ಸಮಸ್ಯೆ
    0.48
     দিনের
    0.48
     ஆகும்
    0.48
     prawdopod
    0.48
     yük
    0.48
     แห
    0.47
    Activations Density 0.000%

    No Known Activations