© 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. 40-GEMMASCOPE-2-RES-262K
    7. 28343
    Prev
    Next
    INDEX
    Explanations

    script tags

    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_40_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
     jQuery
    0.48
     Bd
    0.47
    vil
    0.46
     CDN
    0.45
    Amer
    0.42
     Amer
    0.40
     intolerance
    0.40
    @
    0.40
    bare
    0.40
     Lite
    0.40
    POSITIVE LOGITS
    鿢
    0.41
    బ్బ
    0.39
     medición
    0.39
     функций
    0.38
     экране
    0.38
    sampling
    0.38
    履行
    0.38
    목
    0.38
    ிற்ப
    0.37
    変化
    0.37
    Activations Density 0.001%

    No Known Activations