© 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. 34-GEMMASCOPE-RES-131K
    7. 99711
    Prev
    Next
    INDEX
    Explanations

    sesquiterpene or equine

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

    This neuron activates for the syllable "qu" in words, particularly in academic, scientific, or proper name contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     Juden
    -0.76
    悟
    -0.75
     Feind
    -0.71
    いますが
    -0.69
     لها
    -0.68
     heavily
    -0.68
    ？」
    -0.66
     unless
    -0.66
     enforce
    -0.65
    gs
    -0.64
    POSITIVE LOGITS
    uq
    0.90
    hatsu
    0.85
    łyn
    0.85
     liquidation
    0.83
    CURLOPT
    0.82
    ês
    0.81
    quillas
    0.81
     qu
    0.81
    qu
    0.80
    oine
    0.80
    Activations Density 0.036%

    No Known Activations