© 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. 13-GEMMASCOPE-2-RES-16K
    7. 8989
    Prev
    Next
    INDEX
    Explanations

    time periods and other languages

    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_13_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
     ViewData
    1.31
    窓
    1.30
    上面的
    1.25
    点击
    1.24
    pwm
    1.24
    ع
    1.24
     Visitor
    1.23
     Nederlands
    1.23
     Knitting
    1.23
    眼
    1.21
    POSITIVE LOGITS
    ónica
    1.31
     tetrach
    0.99
    ónicas
    0.98
     aten
    0.97
     tụ
    0.96
     vũ
    0.96
    ਾਰੇ
    0.96
     chum
    0.95
    fillRect
    0.94
    iguë
    0.94
    Activations Density 0.003%

    No Known Activations