© 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. 199245
    Prev
    Next
    INDEX
    Explanations

    common English words and phrases

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

    different angles and lists

    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
    ي
    0.55
    م
    0.48
    滅
    0.48
    м
    0.47
    MENT
    0.46
     incess
    0.46
    י
    0.46
     recognises
    0.45
     විශ
    0.45
    ਾਲ
    0.44
    POSITIVE LOGITS
    ských
    0.50
    !=
    0.48
    winkel
    0.47
     Begriff
    0.46
    TComponent
    0.46
     ব্রাহ্মণ
    0.46
    Bracketing
    0.46
    wirtschaft
    0.45
     রান্না
    0.45
    上下文
    0.44
    Activations Density 0.001%

    No Known Activations