© 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. 14735
    Prev
    Next
    INDEX
    Explanations

    describing function arguments

    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
    一个
    1.12
    ০
    0.99
    ي
    0.97
    Callback
    0.97
    و
    0.96
    一個
    0.94
    Coord
    0.92
    ৭
    0.91
    ைப்
    0.90
     باسک
    0.90
    POSITIVE LOGITS
    тяну
    0.94
    шо
    0.91
    َی
    0.90
    ,”
    0.90
    stwa
    0.87
     биографи
    0.81
    کنند
    0.80
    falls
    0.80
    магази
    0.79
     salari
    0.79
    Activations Density 0.071%

    No Known Activations