© 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. 94295
    Prev
    Next
    INDEX
    Explanations

    wasting time

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

    recommendations for positions/programs

    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
    룀
    0.56
    뭡
    0.53
    イ
    0.52
     публику
    0.50
    ু
    0.50
    უტ
    0.49
    今年の
    0.49
    栦
    0.49
    ৌজের
    0.48
    ות
    0.48
    POSITIVE LOGITS
    kent
    0.48
    intestinal
    0.45
    kne
    0.45
    black
    0.44
    cel
    0.44
    ften
    0.44
    pointed
    0.42
    Fc
    0.42
    downloader
    0.41
    pie
    0.41
    Activations Density 0.000%

    No Known Activations