© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 185549
    Prev
    Next
    INDEX
    Explanations

    a crying

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

    T. rex and dinosaurs

    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
    Negative Logits
    5
    0.48
    0
    0.44
     synchrotron
    0.42
    详细
    0.41
     getDateTime
    0.41
     Điện
    0.41
    संध
    0.40
    купно
    0.40
    )[
    0.39
     되겠죠
    0.39
    POSITIVE LOGITS
    اسية
    0.59
    Animating
    0.49
     potuto
    0.48
    يل
    0.47
     egip
    0.47
    BURSE
    0.44
     effettu
    0.43
    كمة
    0.43
     cancerous
    0.43
     ilegal
    0.43
    Activations Density 0.000%

    No Known Activations