© 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. 174113
    Prev
    Next
    INDEX
    Explanations

    final year-end list

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

    key conventions, tropes, items, owner

    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
    ا
    0.53
     január
    0.50
    Ꮡ
    0.50
     dựa
    0.50
    Based
    0.49
    గ
    0.49
     lundi
    0.48
    લ
    0.48
     سط
    0.47
     abuso
    0.47
    POSITIVE LOGITS
    erves
    0.47
    areti
    0.47
    ides
    0.46
    izzes
    0.46
     watery
    0.45
     hydrates
    0.45
     Yeti
    0.45
     彩
    0.44
    hearing
    0.44
    pares
    0.44
    Activations Density 0.000%

    No Known Activations