© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81943
    Prev
    Next
    INDEX
    Explanations

    Russian and Chinese characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ॒
    0.50
     दिलाया
    0.48
    elivery
    0.48
    igamma
    0.46
    :=\
    0.45
     ത
    0.44
    gal
    0.43
    മ്മി
    0.43
     :=\
    0.43
     इंजन
    0.42
    POSITIVE LOGITS
    s
    0.47
    企
    0.47
    ре
    0.45
    馁
    0.45
     здра
    0.43
     depre
    0.42
     здрав
    0.41
     доктор
    0.41
    踪
    0.41
    рас
    0.41
    Activations Density 0.001%

    No Known Activations