© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1494
    Prev
    Next
    INDEX
    Explanations

    of these or of them

    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
     내
    2.02
    내
    1.95
     어
    1.93
    移
    1.91
     해
    1.89
    கு
    1.83
    spread
    1.80
    ঞ্চল্য
    1.78
    াক
    1.78
    grow
    1.76
    POSITIVE LOGITS
    ی
    2.90
    ्
    2.78
    дже
    2.77
    ორციელ
    2.76
    ть
    2.75
    جات
    2.73
    ្នុង
    2.67
    र
    2.66
    ે
    2.61
    加坡
    2.58
    Activations Density 0.490%

    No Known Activations