© 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. 9279
    Prev
    Next
    INDEX
    Explanations

    ASCII art representation

    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
    
    1.48
    dag
    1.46
    кну
    1.39
    кает
    1.34
    ను
    1.34
     вре
    1.30
    یکن
    1.29
    化した
    1.28
    НУ
    1.28
    妝
    1.26
    POSITIVE LOGITS
    zaXRvcn
    1.46
    ুতি
    1.35
     법칙
    1.29
    ਆ
    1.25
    σωπ
    1.22
    Walls
    1.22
    ofthe
    1.19
     মার্কেটিং
    1.19
    쩡
    1.16
     Walls
    1.15
    Activations Density 0.056%

    No Known Activations