© 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
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2754
    Prev
    Next
    INDEX
    Explanations

    instructions available

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     जिसने
    0.70
    珅
    0.69
     উদ্বিগ্ন
    0.64
     হইল
    0.63
    震惊
    0.62
     হচ্ছেন
    0.61
    య
    0.61
    ৃতির
    0.59
    꿉
    0.58
    轻轻
    0.58
    POSITIVE LOGITS
     available
    5.69
    available
    5.47
     Available
    5.27
    Available
    5.22
     AVAILABLE
    4.93
     disponible
    4.93
     availability
    4.77
     disponibles
    4.69
     disponível
    4.54
    AVAILABLE
    4.45
    Activations Density 1.591%

    No Known Activations