© 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. 64615
    Prev
    Next
    INDEX
    Explanations

    as parameter or argument

    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
    枇
    -0.92
    νομα
    -0.81
     shaker
    -0.77
     midday
    -0.73
     confess
    -0.73
    ChrTalk
    -0.72
     pregă
    -0.72
     ANNOUNC
    -0.71
    atissimo
    -0.70
     medley
    -0.68
    POSITIVE LOGITS
     parameter
    4.81
    参数
    4.47
     argument
    4.25
     parameters
    4.09
     arguments
    3.89
     param
    3.75
     Parameter
    3.61
    parameter
    3.56
     аргу
    3.42
    argument
    3.41
    Activations Density 0.276%

    No Known Activations