© 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. 17-GEMMASCOPE-2-RES-16K
    7. 8878
    Prev
    Next
    INDEX
    Explanations

    language correction and education

    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_17_width_16k_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
     Франция
    1.06
     Согласно
    0.95
    Pokémon
    0.94
    าร์
    0.93
    วิ
    0.91
    Е
    0.87
    atars
    0.86
    Р
    0.86
    รู
    0.84
     액세
    0.84
    POSITIVE LOGITS
     المف
    0.77
     /
    0.76
     sake
    0.76
     inter
    0.76
     ঘৃণা
    0.75
     linguistic
    0.75
     divine
    0.74
     grammar
    0.74
     concat
    0.73
     yap
    0.71
    Activations Density 0.000%

    No Known Activations