© 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. 22-GEMMASCOPE-2-RES-262K
    7. 6046
    Prev
    Next
    INDEX
    Explanations

    code iteration and checks

    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_22_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
    发生了
    1.24
    𝙤
    1.07
    summon
    1.03
     следует
    1.01
    𝙙
    1.01
     DIFFER
    1.00
    ಪ
    0.99
     Sav
    0.95
     gstlal
    0.95
    𝑜
    0.95
    POSITIVE LOGITS
    ega
    0.87
    보기
    0.82
     radia
    0.81
    GPa
    0.81
     지나
    0.78
     件
    0.78
    مج
    0.77
     Verkehrs
    0.77
     turista
    0.76
    adol
    0.76
    Activations Density 0.001%

    No Known Activations