© 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. 7562
    Prev
    Next
    INDEX
    Explanations

    number <=

    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
    eigen
    0.96
     гостей
    0.93
    ا
    0.93
     visitors
    0.92
    众人
    0.92
    此
    0.91
    delt
    0.91
     invaders
    0.90
     voyez
    0.86
    答案
    0.86
    POSITIVE LOGITS
    胧
    1.03
    stof
    0.93
    스
    0.92
     hexagonal
    0.90
     iar
    0.89
     Luz
    0.89
    Programme
    0.87
     cabe
    0.87
    abilité
    0.86
     FH
    0.85
    Activations Density 0.001%

    No Known Activations