© 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. 98572
    Prev
    Next
    INDEX
    Explanations

    required by law, to prevent, YouTube thumbnail, save your, Yak men, train in

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

    alexandrines

    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
    وريا
    0.54
    ة
    0.51
    тон
    0.50
    ты
    0.48
    ﺗ
    0.48
     viss
    0.48
    мана
    0.48
    љи
    0.48
    эф
    0.48
    のひとつ
    0.47
    POSITIVE LOGITS
    gus
    0.52
    i
    0.49
     Galbraith
    0.46
    I
    0.46
    দ্ব
    0.46
    KI
    0.44
    AL
    0.44
    g
    0.43
    ID
    0.43
    dag
    0.42
    Activations Density 0.000%

    No Known Activations