© 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. 153287
    Prev
    Next
    INDEX
    Explanations

    my Bandscans Page

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

    understanding current events

    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
     божо
    0.52
     memastikan
    0.50
     krishna
    0.49
     ভিত্ত
    0.48
     來
    0.48
     Rohit
    0.47
     Mitgl
    0.47
     sør
    0.47
     itth
    0.47
     ので
    0.46
    POSITIVE LOGITS
    و
    0.61
    者
    0.51
    ور
    0.50
     adverse
    0.50
    Deux
    0.48
     increments
    0.46
    "
    0.46
    {
    0.45
    绫
    0.45
    கூ
    0.45
    Activations Density 0.000%

    No Known Activations