© 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. 10-GEMMASCOPE-RES-131K
    7. 128374
    Prev
    Next
    INDEX
    Explanations

    Torres, Dian, outfield, Tia, triage

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

    This neuron strongly activates on occurrences of the surname “Torres.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    𖡼
    -2.83
     That
    -2.73
    ции
    -2.66
     Surprisingly
    -2.66
     Those
    -2.53
    ↵
    -2.50
     These
    -2.38
    ⩩
    -2.38
    握手
    -2.38
     Unlike
    -2.34
    POSITIVE LOGITS
    ㈮
    3.00
    苼
    3.00
    簠
    2.81
    阏
    2.69
    geſ
    2.67
    ࿊
    2.63
    僦
    2.56
    ſſel
    2.56
    ⽆
    2.55
     \"
    2.53
    Activations Density 0.019%

    No Known Activations