© 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. 207156
    Prev
    Next
    INDEX
    Explanations

    places and directions

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

    developed by, created by, early influences

    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
     yemek
    0.48
     mekanisme
    0.48
    arsipkan
    0.48
     रात्री
    0.47
    飯店
    0.47
     struktur
    0.47
     novela
    0.47
    ੧
    0.46
     fragen
    0.46
     شاید
    0.46
    POSITIVE LOGITS
    居
    0.49
    ric
    0.48
    д
    0.48
    ース
    0.46
     союз
    0.45
    ZB
    0.45
    ق
    0.45
    Kam
    0.44
    dyn
    0.44
    బి
    0.44
    Activations Density 0.001%

    No Known Activations