© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 7054
    Prev
    Next
    INDEX
    Explanations

    journey's challenges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    auro
    1.78
    arccos
    1.74
    microseconds
    1.69
    aret
    1.68
    роки
    1.68
    kurat
    1.67
    ″
    1.66
     calibrations
    1.66
    coroutines
    1.63
     intermediates
    1.63
    POSITIVE LOGITS
    势力
    1.36
    andering
    1.33
    낌
    1.21
    oughed
    1.21
    cester
    1.18
    구요
    1.15
    ighed
    1.15
     existente
    1.14
    anderen
    1.14
     있던
    1.12
    Activations Density 0.013%

    No Known Activations