© 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. 41-GEMMASCOPE-2-RES-262K
    7. 5982
    Prev
    Next
    INDEX
    Explanations

    legal/scientific terminology

    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_all/layer_41_width_262k_l0_big
    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
     -"
    0.45
    uyor
    0.43
     concurred
    0.42
     ."
    0.41
     concurs
    0.41
     および
    0.41
     ай
    0.41
    IFORN
    0.40
     verhind
    0.40
     일이
    0.40
    POSITIVE LOGITS
    錯
    0.43
     balance
    0.42
    اعت
    0.42
    ক্ষ
    0.41
    ADS
    0.40
    ై
    0.40
    記
    0.40
    ги
    0.39
    επ
    0.39
     traite
    0.39
    Activations Density 0.000%

    No Known Activations