© 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. 5060
    Prev
    Next
    INDEX
    Explanations

    children and babies

    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
     penerapan
    0.75
     Corrosion
    0.73
     चना
    0.71
     এড়িয়ে
    0.70
     वापर
    0.70
     corrosion
    0.70
    ^{\#}\
    0.70
    失效
    0.67
     الشركات
    0.67
    座標
    0.67
    POSITIVE LOGITS
     babies
    2.32
     baby
    2.29
     offspring
    2.21
     newborns
    2.11
     newborn
    2.02
    baby
    1.96
     Baby
    1.95
     bebé
    1.95
     infants
    1.94
    Baby
    1.92
    Activations Density 0.095%

    No Known Activations