© 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. 26148
    Prev
    Next
    INDEX
    Explanations

    division of joints and marrow

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

    understand career path

    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
    یک
    0.48
    طر
    0.45
    وی
    0.45
    ویی
    0.44
    ת
    0.44
     سے
    0.44
     hukum
    0.43
    من
    0.42
    وجد
    0.42
    بط
    0.42
    POSITIVE LOGITS
    attro
    0.50
     апо
    0.50
     À
    0.49
    textcolor
    0.49
    writer
    0.47
    merk
    0.47
    artists
    0.47
    spath
    0.46
    platforms
    0.46
    mounted
    0.46
    Activations Density 0.000%

    No Known Activations