© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128364
    Prev
    Next
    INDEX
    Explanations

    countries and geopolitical entities

    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
    Not in Any Lists

    No Comments

    Negative Logits
     our
    -2.23
     навіть
    -1.99
    Both
    -1.84
     дуже
    -1.82
     these
    -1.75
     céu
    -1.71
    Sometimes
    -1.67
     TÉCNICA
    -1.66
     both
    -1.63
     більше
    -1.63
    POSITIVE LOGITS
     will
    2.11
     nadat
    1.55
    
    1.50
     hopes
    1.47
     destined
    1.46
     veilig
    1.45
     voordat
    1.45
     permettra
    1.44
     expected
    1.43
     veroor
    1.43
    Activations Density 0.407%

    No Known Activations