© 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. 10-GEMMASCOPE-RES-131K
    7. 90755
    Prev
    Next
    INDEX
    Explanations

    webkit modularization

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on numeric literals (especially floating-point/decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     sociala
    -1.84
     obiet
    -1.80
    тием
    -1.75
     déchir
    -1.74
     Houſe
    -1.73
    ÑOS
    -1.71
     répand
    -1.66
    ación
    -1.62
    ərbaycan
    -1.55
     wirklich
    -1.54
    POSITIVE LOGITS
     “
    1.77
    也能
    1.73
    4
    1.66
    ”،
    1.63
     order
    1.58
    算是
    1.57
     we
    1.57
    見ると
    1.52
     unn
    1.52
     AWAY
    1.51
    Activations Density 0.001%

    No Known Activations