© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59095
    Prev
    Next
    INDEX
    Explanations

    annual meetings and conferences

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

    The neuron detects references to academic or professional conference events—especially “Annual Meeting”‐style names, dates, and related numeric tokens.

    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
     broth
    -0.78
    fashion
    -0.77
    opers
    -0.77
    ージュ
    -0.75
     necessary
    -0.73
    /?
    -0.70
    chowa
    -0.70
     permitido
    -0.70
    uge
    -0.69
     filling
    -0.69
    POSITIVE LOGITS
     meeting
    1.74
     meetings
    1.57
    Meeting
    1.49
     Meetings
    1.45
    meeting
    1.37
     Meeting
    1.37
    Meetings
    1.31
     annual
    1.20
     MEETING
    1.16
    meetings
    1.16
    Activations Density 0.024%

    No Known Activations