© 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. 9647
    Prev
    Next
    INDEX
    Explanations

    names and titles

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

    This neuron detects multi‐token proper names and other named-entity phrases—such as persons, places, organizations, or titles.

    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
     if
    -1.94
     \
    -1.66
    ="
    -1.66
     in
    -1.64
     If
    -1.62
     at
    -1.52
     by
    -1.51
    )
    -1.48
     |
    -1.48
    »
    -1.47
    POSITIVE LOGITS
    のかもしれません
    1.66
    麃
    1.63
     indisponible
    1.53
     réinitial
    1.53
    どうやって
    1.50
    見た
    1.49
    usehen
    1.47
     całym
    1.47
    lleg
    1.45
     superbes
    1.45
    Activations Density 1.408%

    No Known Activations