© 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. 67881
    Prev
    Next
    INDEX
    Explanations

    head of department or organization

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

    The neuron activates on occurrences of the phrase “head of” when introducing a person’s title or leadership role.

    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
    .
    -3.50
    )
    -2.55
    vantaged
    -2.34
    ”
    -2.13
     gewiß
    -1.97
    <i>
    -1.95
    ."
    -1.92
    ;
    -1.88
    autogui
    -1.86
    Figure
    -1.76
    POSITIVE LOGITS
    Ꮉ
    2.83
     プレミアム
    2.22
    most
    2.19
     wth
    2.09
     esperienza
    2.08
     imágen
    2.03
    蔀
    2.00
    们
    1.98
    檍
    1.95
    沇
    1.95
    Activations Density 0.007%

    No Known Activations