© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 149438
    Prev
    Next
    INDEX
    Explanations

    pygame.display.flip or set

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
    㥳
    0.75
     Tolerance
    0.75
     Preference
    0.74
     Reducing
    0.73
    อาด
    0.71
     Goal
    0.71
     ಥ
    0.71
    浾
    0.71
    澫
    0.70
     sis
    0.70
    POSITIVE LOGITS
    mixin
    0.63
    प्पा
    0.63
    mie
    0.62
     Mille
    0.62
    feira
    0.61
    ട്ര
    0.61
    dre
    0.60
    kee
    0.59
    mil
    0.59
    mf
    0.58
    Activations Density 0.001%

    No Known Activations