© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 12569
    Prev
    Next
    INDEX
    Explanations

    word definition and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    y
    0.85
     структуру
    0.83
    ignature
    0.82
     CH
    0.79
     MEGA
    0.77
    齙
    0.76
    estruct
    0.76
    yong
    0.75
     BASIS
    0.75
    yed
    0.75
    POSITIVE LOGITS
    دي
    0.92
    ди
    0.91
    Desde
    0.90
    Теперь
    0.90
    О
    0.88
    昨年
    0.87
    닳
    0.87
    時間
    0.86
    誰
    0.86
    Dé
    0.85
    Activations Density 0.000%

    No Known Activations