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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109585
    Prev
    Next
    INDEX
    Explanations

    best in class

    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_34/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
     great
    -1.09
     uñas
    -1.09
     emisiones
    -1.07
     rodillas
    -1.04
     ganancias
    -1.04
     ventilación
    -1.01
    那些
    -0.99
     burbujas
    -0.96
    Når
    -0.96
    kelt
    -0.94
    POSITIVE LOGITS
     in
    2.52
     ever
    2.47
     among
    2.25
     of
    1.95
     amongst
    1.74
     среди
    1.74
    among
    1.53
     parmi
    1.50
     EVER
    1.45
    ever
    1.31
    Activations Density 0.080%

    No Known Activations