© 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. 64132
    Prev
    Next
    INDEX
    Explanations

    White House

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

    The neuron specifically detects occurrences of the word “White.”

    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
    zzlement
    -0.81
     trener
    -0.73
    wortet
    -0.71
     transmis
    -0.71
     criterio
    -0.70
    干燥
    -0.70
    aturas
    -0.69
    今回
    -0.69
    muje
    -0.68
    静岡
    -0.68
    POSITIVE LOGITS
    house
    1.23
     house
    1.06
    head
    1.05
     House
    1.04
    House
    1.03
    lettre
    0.87
    HOUSE
    0.86
    header
    0.84
    hurst
    0.79
     ház
    0.78
    Activations Density 0.042%

    No Known Activations