© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 47976
    Prev
    Next
    INDEX
    Explanations

    foreign languages and work

    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_16_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
    rives
    0.49
    接続
    0.49
    sschutz
    0.48
    on
    0.47
    ковник
    0.47
     कुलपति
    0.46
    防
    0.46
    summ
    0.45
    ክር
    0.45
    urrection
    0.45
    POSITIVE LOGITS
    תי
    0.63
     nello
    0.60
    АН
    0.54
     strada
    0.52
     campione
    0.52
    اری
    0.50
     daffodils
    0.50
     രണ്ടു
    0.49
     lanes
    0.49
    Μ
    0.49
    Activations Density 0.000%

    No Known Activations