© 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. 79050
    Prev
    Next
    INDEX
    Explanations

    foreign language markers

    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
     فیصد
    0.51
     polynomials
    0.45
    ಯ್
    0.45
     aggregated
    0.45
    聵
    0.45
    古い
    0.45
    돼
    0.44
     кере
    0.44
     associativity
    0.44
     salesperson
    0.43
    POSITIVE LOGITS
    enças
    0.53
    um
    0.48
    ich
    0.46
    au
    0.45
    ুয়া
    0.44
     přes
    0.42
     été
    0.42
    ované
    0.42
     média
    0.41
    f
    0.41
    Activations Density 0.000%

    No Known Activations