© 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. 130294
    Prev
    Next
    INDEX
    Explanations

    days are, rules governing, jeans can, create significant

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

    Angular orbits trajectories

    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
    ۞
    0.48
     lọ
    0.46
     વૃ
    0.45
    <unused56>
    0.45
     интернете
    0.44
     платформа
    0.44
     нее
    0.44
     与
    0.43
     наме
    0.43
     сервера
    0.43
    POSITIVE LOGITS
    a
    0.54
    ش
    0.52
     trajectories
    0.51
    ور
    0.49
    orbits
    0.49
    ان
    0.49
    w
    0.47
    十足
    0.47
    C
    0.46
    ظل
    0.46
    Activations Density 0.000%

    No Known Activations