© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 144271
    Prev
    Next
    INDEX
    Explanations

    all you

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

    thalidomide and related drugs

    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
    Negative Logits
     &/
    0.49
    もし
    0.45
    ائیو
    0.43
    вето
    0.43
    TestSource
    0.43
     ощу
    0.42
    өм
    0.42
     rewire
    0.42
    列車
    0.42
    āli
    0.41
    POSITIVE LOGITS
    所有
    0.48
     Vando
    0.47
    分
    0.46
    C
    0.46
     vezes
    0.45
     Dijon
    0.45
    toare
    0.44
    caller
    0.44
    Ah
    0.44
    对
    0.44
    Activations Density 0.001%

    No Known Activations