© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10721
    Prev
    Next
    INDEX
    Explanations

    в качестве

    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_22_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
     внутрен
    1.07
     namin
    0.95
     Фран
    0.92
    or
    0.86
    Ꮏ
    0.86
     Второй
    0.86
     در
    0.85
     в
    0.85
     въ
    0.85
    ސ
    0.84
    POSITIVE LOGITS
     рамках
    1.55
     соответствии
    1.36
     rámci
    1.36
     meantime
    1.21
     условиях
    1.20
     результате
    1.20
     tomto
    1.17
     наличии
    1.16
     итоге
    1.16
     мире
    1.15
    Activations Density 0.019%

    No Known Activations