© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14316
    Prev
    Next
    INDEX
    Explanations

    units and large numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     配置
    1.53
     删除
    1.38
     НЕ
    1.35
     항공
    1.33
    াইব
    1.32
    :[/
    1.31
     Одна
    1.30
     허
    1.29
     НА
    1.29
    Одна
    1.27
    POSITIVE LOGITS
     geral
    1.46
     autre
    1.40
     infancia
    1.40
     sayang
    1.33
     secretário
    1.33
     général
    1.33
     incroyable
    1.32
     cerrado
    1.32
     gerais
    1.31
     riqueza
    1.31
    Activations Density 0.114%

    No Known Activations