© 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. 167473
    Prev
    Next
    INDEX
    Explanations

    to attempt

    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
     付
    0.39
    尔
    0.39
    æ
    0.38
    獲
    0.38
    ઞ
    0.38
    Ар
    0.37
    转
    0.37
    爾
    0.37
    ÇÃO
    0.36
    दिल
    0.36
    POSITIVE LOGITS
    னவே
    0.43
     shaft
    0.43
     recipes
    0.41
     four
    0.41
     patru
    0.41
     postal
    0.40
    เข้ามา
    0.40
     Camel
    0.40
     ریز
    0.40
     Page
    0.40
    Activations Density 0.000%

    No Known Activations