© 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. 64371
    Prev
    Next
    INDEX
    Explanations

    Qin, Abandonment, Skin, Package, Special

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

    The neuron is selectively activated by the tokens making up the Chinese name “Qin Kanying,” i.e. it flags occurrences of that proper name.

    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
    庾
    -0.92
    菰
    -0.77
     COMMIT
    -0.76
    género
    -0.74
     柏
    -0.73
    хід
    -0.73
     lengthwise
    -0.73
    ¿
    -0.72
    ல்ல
    -0.71
     Snape
    -0.71
    POSITIVE LOGITS
    ối
    0.85
     edifici
    0.82
     przeci
    0.77
     OnTriggerEnter
    0.75
    Qin
    0.75
    RestTemplate
    0.73
     ADVISORY
    0.73
    옴
    0.73
    най
    0.71
    イヤル
    0.70
    Activations Density 0.000%

    No Known Activations