© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91617
    Prev
    Next
    INDEX
    Explanations

    code includes and definitions

    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
     additional
    -0.96
     because
    -0.93
    甕
    -0.84
     dozens
    -0.83
     derselbe
    -0.82
    imagens
    -0.80
    sqlQuery
    -0.79
     Matt
    -0.79
     Additional
    -0.79
    ulico
    -0.77
    POSITIVE LOGITS
    include
    2.70
     include
    2.52
     includes
    1.68
     включа
    1.64
    Include
    1.63
     incluyen
    1.59
    includes
    1.50
     Include
    1.47
    INCLUDE
    1.45
     included
    1.44
    Activations Density 0.033%

    No Known Activations