© 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. 38127
    Prev
    Next
    INDEX
    Explanations

    cyclone, hurricane, typhoon names

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

    The neuron detects mentions of named tropical cyclones (e.g. “Super-typhoon Haiyan”).

    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
     września
    -0.79
     Egyptian
    -0.79
     Federal
    -0.75
    ｙ
    -0.74
     Heritage
    -0.74
     tiek
    -0.74
     Gates
    -0.73
     Cure
    -0.73
     federal
    -0.72
    >',
    -0.71
    POSITIVE LOGITS
    DOCX
    0.95
     perfet
    0.82
     traw
    0.82
     nutty
    0.80
     Typhoon
    0.80
     Buffy
    0.79
     ciné
    0.78
     FISHER
    0.77
     MONTHLY
    0.76
     chargeur
    0.75
    Activations Density 0.011%

    No Known Activations