© 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. 10-GEMMASCOPE-RES-131K
    7. 103111
    Prev
    Next
    INDEX
    Explanations

    Torres and Rogers names

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

    The neuron is strongly activated by capitalized personal surnames (i.e. people’s last names).

    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
    0
    -3.78
     ERSITY
    -2.98
    捽
    -2.89
     RSITY
    -2.78
    犽
    -2.78
    for
    -2.72
     IBRARY
    -2.44
    The
    -2.44
    賒
    -2.41
    the
    -2.34
    POSITIVE LOGITS
    轳
    2.98
    瑒
    2.97
    archiwizowane
    2.92
    花の
    2.83
     ก็
    2.77
     Что
    2.59
    たの
    2.53
     fatos
    2.47
    阗
    2.39
    亹
    2.39
    Activations Density 0.003%

    No Known Activations