© 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. 73313
    Prev
    Next
    INDEX
    Explanations

    religious teachings and teachers

    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
    鋱
    -2.02
     jambe
    -1.92
     couverts
    -1.85
    arraycopy
    -1.83
     fumée
    -1.80
    ઈ
    -1.74
    '
    -1.74
    过程中
    -1.74
    struktion
    -1.73
    쥘
    -1.73
    POSITIVE LOGITS
    ↵↵
    2.41
     verbess
    2.00
     about
    1.95
    ”;
    1.81
     Schluß
    1.77
     Tento
    1.76
     Veränder
    1.74
     Herausgeber
    1.73
     of
    1.72
     they
    1.70
    Activations Density 0.008%

    No Known Activations