© 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. 179169
    Prev
    Next
    INDEX
    Explanations

    performance and measurements

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

    error message if

    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
    leaders
    0.44
    second
    0.44
    ↵↵
    0.43
     voglio
    0.43
    rev
    0.41
    team
    0.41
     leaders
    0.40
     вышел
    0.40
     I
    0.40
     तत्काल
    0.39
    POSITIVE LOGITS
    ClInclude
    0.55
    Penumpang
    0.52
    स्करी
    0.51
    ProductId
    0.50
     কেবলমাত্র
    0.49
    ূল্য
    0.49
    ثنين
    0.47
     capacitances
    0.46
    ClF
    0.46
     errone
    0.45
    Activations Density 0.000%

    No Known Activations