© 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. 34-GEMMASCOPE-RES-131K
    7. 90719
    Prev
    Next
    INDEX
    Explanations

    town hall and round table

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

    This neuron detects the initial word in common two-word collocations for meetings, events, or venues (e.g. “town hall,” “round table,” “brown bag,” “town house”).

    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
    時半
    -0.78
     anonymous
    -0.72
    ﾆ
    -0.72
     acronyms
    -0.71
    mosa
    -0.71
     modest
    -0.69
     sick
    -0.69
     triplicate
    -0.69
    したが
    -0.68
    暢
    -0.68
    POSITIVE LOGITS
    table
    1.03
    hall
    0.98
     table
    0.82
    tables
    0.82
     discuss
    0.77
     hall
    0.75
     Table
    0.74
    tabel
    0.73
     halls
    0.73
    ähle
    0.73
    Activations Density 0.067%

    No Known Activations