© 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. 29991
    Prev
    Next
    INDEX
    Explanations

    jamming radius

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

    countries and regions

    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
     assuntos
    0.38
     ennemis
    0.35
     qnt
    0.34
     évén
    0.33
     zawier
    0.33
     misfortunes
    0.32
    指数
    0.32
     شئ
    0.31
    ⺝
    0.31
     قوت
    0.31
    POSITIVE LOGITS
     Vietnam
    0.40
    0.38
     Australia
    0.36
     Cambodia
    0.35
     Thailand
    0.35
     Somalia
    0.34
     America
    0.34
     Nepal
    0.34
     also
    0.34
     high
    0.34
    Activations Density 0.030%

    No Known Activations