Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 1077
    Prev
    Next
    INDEX
    Explanations

    yoga poses or asanas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_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
    بہ
    0.51
    ATIC
    0.49
    बे
    0.48
    ೂರ್
    0.48
    மாக
    0.47
     Kaise
    0.47
    𝕐
    0.47
     Tecn
    0.47
    ম্বে
    0.47
     Teknologi
    0.47
    POSITIVE LOGITS
    <0x0D>
    0.67
     على
    0.60
    ق
    0.54
     هو
    0.54
    </h4>
    0.53
    promises
    0.50
     мы
    0.50
     получится
    0.49
    plants
    0.48
     ondas
    0.48
    Activations Density 0.002%

    No Known Activations