© 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. 187298
    Prev
    Next
    INDEX
    Explanations

    This is amazing or down over

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

    this followed by positive descriptor

    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
    泫
    0.50
    <unused97>
    0.49
     effectuer
    0.49
    રિક
    0.49
    滘
    0.47
    <unused70>
    0.46
     prestataire
    0.46
     اكس
    0.46
    <unused43>
    0.46
     resear
    0.46
    POSITIVE LOGITS
     た
    0.44
     &
    0.44
     D
    0.43
     वीर
    0.43
    verbose
    0.42
    まれ
    0.41
    の上
    0.41
     Dill
    0.41
    askell
    0.41
    angular
    0.40
    Activations Density 0.000%

    No Known Activations