© 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. 246780
    Prev
    Next
    INDEX
    Explanations

    designed luxury

    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
    に対応
    0.53
    یل
    0.52
    த்தைக்
    0.51
     Silverstone
    0.50
    鬯
    0.50
     JCV
    0.50
    ທາງ
    0.49
    の使用
    0.49
    стра
    0.48
    стта
    0.47
    POSITIVE LOGITS
    topnav
    0.46
     conditioners
    0.45
    Dieses
    0.44
     ಅವನ
    0.42
     hints
    0.42
    Cuáles
    0.41
     tabs
    0.41
    Á
    0.41
     chips
    0.41
    Reli
    0.40
    Activations Density 0.000%

    No Known Activations