© 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. 44319
    Prev
    Next
    INDEX
    Explanations

    anonymous functions or closures

    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
     görüntüleri
    -1.84
    蜮
    -1.80
     flera
    -1.77
     detayl
    -1.77
     kült
    -1.73
     verschillende
    -1.67
    ’，
    -1.66
    ↀ
    -1.59
    ctar
    -1.58
     adecuados
    -1.58
    POSITIVE LOGITS
    (
    2.38
    >
    2.03
     in
    1.99
    :
    1.91
    ()
    1.84
     も
    1.67
     for
    1.59
     this
    1.59
    \
    1.54
     his
    1.51
    Activations Density 0.012%

    No Known Activations