© 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. 142462
    Prev
    Next
    INDEX
    Explanations

    before making decisions or continuing

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

    diving into specifics

    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
    Not in Any Lists

    No Comments

    Negative Logits
     أثناء
    0.46
     animate
    0.45
     뿐
    0.44
     வாழ
    0.43
     zowel
    0.43
    人不
    0.43
     ઉપરાંત
    0.41
     तथा
    0.41
    Rio
    0.40
    뿐
    0.40
    POSITIVE LOGITS
     siquiera
    0.58
     any
    0.51
     quelconque
    0.49
     очередной
    0.49
     본격
    0.49
     Fully
    0.45
    各大
    0.44
    উল্লেখ্য
    0.43
     CVE
    0.42
     irreversible
    0.42
    Activations Density 0.077%

    No Known Activations