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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 6148
    Prev
    Next
    INDEX
    Explanations

    natural amounts emitted

    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
    蛯
    0.53
     ശക്ത
    0.52
    ﻡ
    0.51
     tweede
    0.50
     പ്രതീക്ഷ
    0.49
    屋内
    0.48
    COMANDA
    0.47
     wedstrijd
    0.47
     което
    0.46
    安倍
    0.46
    POSITIVE LOGITS
    a
    0.53
     administrators
    0.48
    ↵
    0.47
     pai
    0.47
    ه
    0.46
    user
    0.45
    aires
    0.43
    t
    0.43
    머니
    0.43
     administrator
    0.41
    Activations Density 0.000%

    No Known Activations