© 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. 159952
    Prev
    Next
    INDEX
    Explanations

    world, ideas, reset, urge

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

    refugees, Elite Dangerous, Post-Prison

    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
     Debit
    0.52
    li
    0.51
     Необходимо
    0.50
    s
    0.48
    install
    0.46
     Schall
    0.46
    tab
    0.45
    you
    0.45
     Maintenance
    0.45
     youll
    0.45
    POSITIVE LOGITS
    אה
    0.55
    讨厌
    0.50
    媧
    0.46
    非洲
    0.46
     نکن
    0.46
     sufrir
    0.46
    聝
    0.46
    اداسی
    0.45
    鞅
    0.44
    䬲
    0.44
    Activations Density 0.000%

    No Known Activations