© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 57982
    Prev
    Next
    INDEX
    Explanations

    place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    攫
    -1.90
    婓
    -1.87
     şi
    -1.83
     orthodox
    -1.81
    subequations
    -1.79
    壅
    -1.76
     ajustado
    -1.73
    oporosis
    -1.72
     interpretar
    -1.72
    WTA
    -1.70
    POSITIVE LOGITS
    塒
    2.19
    踯
    2.16
     faisant
    2.11
    ates
    2.08
     But
    1.94
     लेकिन
    1.93
    es
    1.88
    我很
    1.87
    ть
    1.85
    镦
    1.85
    Activations Density 0.041%

    No Known Activations