© 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. 125350
    Prev
    Next
    INDEX
    Explanations

    Trump Administration

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

    problem statement

    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
    рую
    0.55
     පු
    0.46
    ุ
    0.45
    ธี
    0.44
    культур
    0.44
     Britton
    0.43
    ූප
    0.43
    три
    0.43
    кай
    0.42
    ሔ
    0.42
    POSITIVE LOGITS
    ann
    0.49
    小数
    0.49
    戮
    0.49
    加速度
    0.47
    {\'
    0.46
    gras
    0.46
    詬
    0.46
    ade
    0.45
    annon
    0.45
    >/
    0.44
    Activations Density 0.000%

    No Known Activations