© 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. 10955
    Prev
    Next
    INDEX
    Explanations

    show.php news.html

    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
    鑿
    0.46
     fiabilité
    0.45
    鴟
    0.44
     Vasa
    0.44
    speakers
    0.44
    暐
    0.44
    Silent
    0.43
     إيران
    0.43
    瑢
    0.43
    䅛
    0.43
    POSITIVE LOGITS
     $_
    0.47
     think
    0.46
    模型
    0.44
    addons
    0.44
    垃圾
    0.42
     Think
    0.41
    think
    0.41
     jumps
    0.41
    Think
    0.41
    北京
    0.40
    Activations Density 0.001%

    No Known Activations