© 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. 31-GEMMASCOPE-2-RES-262K
    7. 52303
    Prev
    Next
    INDEX
    Explanations

    backtesting, data, measurements

    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
    人为
    0.56
    بال
    0.50
    长
    0.50
    资源
    0.50
    确认
    0.48
    尝试
    0.46
    сті
    0.46
    乔
    0.45
    视
    0.44
    文
    0.43
    POSITIVE LOGITS
    複
    0.48
     clandest
    0.47
     integrand
    0.46
     traitor
    0.46
    রীণ
    0.44
     semic
    0.44
     复
    0.44
    बई
    0.43
    ເວລາ
    0.43
     interpol
    0.43
    Activations Density 0.002%

    No Known Activations