© 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. 112359
    Prev
    Next
    INDEX
    Explanations

    underwent / undergoing

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

    The neuron responds to numeric measurements—especially decimal values embedded in scientific or technical contexts.

    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
    ternut
    -1.98
     также
    -1.88
     couvrir
    -1.87
     también
    -1.82
     też
    -1.78
     também
    -1.77
    vereignty
    -1.77
    termilk
    -1.70
    tocks
    -1.70
     also
    -1.69
    POSITIVE LOGITS
     this
    2.39
     for
    2.22
     now
    1.91
     which
    1.84
     on
    1.77
    ,
    1.69
     out
    1.69
     most
    1.68
     other
    1.63
     who
    1.63
    Activations Density 0.247%

    No Known Activations