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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 78594
    Prev
    Next
    INDEX
    Explanations

    mother nature

    np_acts-logits-general · gemini-2.5-flash-lite

    nature or nature's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    ۔
    0.77
     зрения
    0.65
     irá
    0.64
    ።
    0.63
    는
    0.63
     diverso
    0.62
     envi
    0.61
    ä
    0.60
     начало
    0.58
    的环境
    0.57
    POSITIVE LOGITS
    un
    0.62
    ли
    0.61
    u
    0.60
     ব্যাপকভাবে
    0.60
    le
    0.59
    ot
    0.59
    al
    0.58
    ul
    0.58
     PARK
    0.57
    ’
    0.57
    Activations Density 0.015%

    No Known Activations