© 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. 25662
    Prev
    Next
    INDEX
    Explanations

    Holmes name and GPL license

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

    The neuron is a highly specific detector for the token “Holmes.”

    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
     Кол
    -0.71
     bulb
    -0.70
     glaub
    -0.69
     Verkehr
    -0.68
     Empire
    -0.68
     grateful
    -0.67
     противо
    -0.66
    側
    -0.66
    krivelse
    -0.66
    chien
    -0.64
    POSITIVE LOGITS
     白い
    0.74
    findViewById
    0.72
     Fairbanks
    0.71
    rosio
    0.68
     immobilized
    0.67
    끓
    0.65
    轨道
    0.62
     Secre
    0.62
    atelle
    0.61
    푸
    0.61
    Activations Density 0.103%

    No Known Activations