© 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. 34-GEMMASCOPE-RES-131K
    7. 1863
    Prev
    Next
    INDEX
    Explanations

    theatre and actors

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

    The neuron is primarily detecting named entities—especially proper names of people, organizations, and places.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    畫面
    -0.82
     gdyż
    -0.75
    ingga
    -0.74
    ⑯
    -0.74
    𓏸
    -0.74
     یو
    -0.73
    ♗
    -0.73
    thodon
    -0.73
    ోగ
    -0.73
    êter
    -0.72
    POSITIVE LOGITS
     theatre
    3.41
     theater
    3.09
     actors
    2.92
     Theatre
    2.59
    theatre
    2.53
     theatrical
    2.50
     actor
    2.47
    Theatre
    2.41
     stage
    2.36
     Actors
    2.36
    Activations Density 0.143%

    No Known Activations