© 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. 82743
    Prev
    Next
    INDEX
    Explanations

    Bristol City, University, office

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

    The neuron is selectively activated by occurrences of the place name “Bristol” (and its “Bris-” substring).

    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
     speciation
    -0.81
     prostřed
    -0.78
     zwykle
    -0.76
     embarazadas
    -0.75
     cramps
    -0.74
    кожа
    -0.73
    🏦
    -0.73
    chee
    -0.73
     Melanie
    -0.71
    ախ
    -0.71
    POSITIVE LOGITS
    Maxim
    0.88
    ilities
    0.87
     Bris
    0.86
     gynhyrchwyd
    0.82
    lific
    0.82
     indicating
    0.81
     pasaba
    0.81
     Busy
    0.80
    éis
    0.80
    ){}
    0.79
    Activations Density 0.008%

    No Known Activations