© 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. 4953
    Prev
    Next
    INDEX
    Explanations

    so, app, numbers

    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
     symmetrical
    0.65
     NCB
    0.65
    чом
    0.64
     преимущества
    0.64
    amir
    0.62
    जाम
    0.61
    xsi
    0.61
    Ù
    0.60
     Kirkland
    0.60
    ബ
    0.59
    POSITIVE LOGITS
    FUL
    0.73
     건
    0.73
    ések
    0.71
     geeign
    0.69
    yster
    0.68
    annulation
    0.68
    ETHER
    0.68
    CEP
    0.68
     پیشن
    0.68
     હાથ
    0.67
    Activations Density 0.001%

    No Known Activations