© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 110804
    Prev
    Next
    INDEX
    Explanations

    file paths and options

    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
     فقط
    0.49
    を一
    0.46
     ocurrió
    0.45
    కపో
    0.43
    ✔️
    0.42
     инструмент
    0.40
     dplyr
    0.40
     recurrent
    0.39
     absolument
    0.39
     outflows
    0.39
    POSITIVE LOGITS
     mật
    0.40
    视频
    0.40
     ভিডিও
    0.39
    阂
    0.39
    streets
    0.38
    话说
    0.37
    wedd
    0.37
     địa
    0.37
    dry
    0.37
    园区
    0.37
    Activations Density 0.003%

    No Known Activations