© 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. 123728
    Prev
    Next
    INDEX
    Explanations

    accuracy of reporting

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

    options and lists

    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
     folgender
    0.55
     早
    0.54
     anmelden
    0.53
    Unsere
    0.52
     arbeitet
    0.52
     ぐらい
    0.50
    benzoimidazol
    0.49
     berubah
    0.47
     সোন
    0.47
     急
    0.47
    POSITIVE LOGITS
     their
    0.53
     a
    0.50
    c
    0.50
     sales
    0.48
     poetry
    0.48
     matrimonial
    0.48
     ruler
    0.47
     p
    0.47
    spine
    0.47
     accede
    0.46
    Activations Density 0.000%

    No Known Activations