© 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. 199990
    Prev
    Next
    INDEX
    Explanations

    about your

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

    names and descriptions

    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
     үш
    0.46
    を開
    0.45
    किल
    0.45
    书
    0.44
     نوٹ
    0.43
     کھلا
    0.43
     ይህም
    0.42
    旸
    0.42
    䏌
    0.41
    茟
    0.41
    POSITIVE LOGITS
     Aj
    0.52
     ={
    0.51
    .&
    0.50
    qv
    0.48
     HUMAN
    0.47
     我們
    0.47
    setupUi
    0.47
     zusätzlich
    0.47
     特別
    0.46
     Bers
    0.46
    Activations Density 0.001%

    No Known Activations