© 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. 190758
    Prev
    Next
    INDEX
    Explanations

    chasing experts

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

    lists of items or points

    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
    ’
    0.52
    チェック
    0.51
    จ
    0.50
    公安
    0.49
     eaux
    0.48
     punkt
    0.48
    estris
    0.47
    ’?
    0.46
    ポイント
    0.46
    無線
    0.45
    POSITIVE LOGITS
    يط
    0.48
    ൪
    0.46
    ικοί
    0.44
     toán
    0.44
    ై
    0.44
    al
    0.43
    n
    0.43
     πά
    0.43
    تمبر
    0.43
    rava
    0.43
    Activations Density 0.000%

    No Known Activations