© 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. 67951
    Prev
    Next
    INDEX
    Explanations

    last update date

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

    remove non-breaking spaces

    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
     damning
    0.59
     bisnis
    0.53
     countless
    0.50
     OUR
    0.46
     membuka
    0.45
     tantamount
    0.45
    Ə
    0.45
    겠다는
    0.44
     Tujuan
    0.44
    ॒
    0.44
    POSITIVE LOGITS
     также
    0.52
     également
    0.50
     крайней
    0.49
    igue
    0.48
     також
    0.48
    大约
    0.47
     cũng
    0.47
     ayrıca
    0.47
    에게
    0.46
     holotype
    0.46
    Activations Density 0.001%

    No Known Activations