© 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. 22-GEMMASCOPE-RES-131K
    7. 39043
    Prev
    Next
    INDEX
    Explanations

    hosting visitors at home

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

    The neuron fires on references to sports venues or home/away contexts, such as stadium names and “home” or “visiting” game mentions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     trip
    -0.97
    trip
    -0.92
     unterwegs
    -0.87
    ohist
    -0.85
     traveling
    -0.85
     travel
    -0.82
    extrême
    -0.81
    地说道
    -0.81
    myModal
    -0.79
     Traveling
    -0.79
    POSITIVE LOGITS
     hosting
    1.14
     visitors
    1.11
     welcoming
    1.07
     welcome
    1.06
     welcomes
    1.03
    welcome
    0.97
    Hosting
    0.96
    Visitors
    0.96
     reception
    0.88
     Visitors
    0.88
    Activations Density 0.077%

    No Known Activations