© 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. 97215
    Prev
    Next
    INDEX
    Explanations

    question or certain . or next from

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

    for beginners

    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
    Mj
    0.51
    Tn
    0.50
    𝗡
    0.49
     ಪೂರ್ವ
    0.47
    edom
    0.46
    myd
    0.46
    를
    0.45
    З
    0.45
    Selecion
    0.45
     הז
    0.44
    POSITIVE LOGITS
     ملعب
    0.49
     paddles
    0.47
     jPanel
    0.47
     Paddle
    0.47
     paddle
    0.44
     inflicting
    0.43
     afflicted
    0.43
     vows
    0.41
    实际上
    0.41
     बेसिकली
    0.41
    Activations Density 0.001%

    No Known Activations