© 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. 87171
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

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

    data entry context

    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
     ሚ
    0.45
     ਕੋ
    0.44
     negeri
    0.43
     სტ
    0.43
    様
    0.43
    ոլ
    0.43
     pelt
    0.43
     thousand
    0.42
     저는
    0.42
     コーヒー
    0.42
    POSITIVE LOGITS
     {
    0.55
     Hồng
    0.47
     إعادة
    0.46
     for
    0.45
    我们的
    0.43
    我们
    0.42
    {
    0.42
     dolore
    0.41
    后续
    0.41
    ды
    0.41
    Activations Density 0.000%

    No Known Activations