© 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. 128024
    Prev
    Next
    INDEX
    Explanations

    Vanderbilt family and related names

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

    The neuron activates on the token sequences referring to “Vanderbilt” (the university, medical center, or people/places named Vanderbilt).

    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
     nghiệ
    -2.53
     they
    -2.47
    鳢
    -2.27
    P
    -2.27
    是被
    -2.27
    咘
    -2.22
    ulée
    -2.19
     入り口
    -2.16
     delimiter
    -2.14
    ᷆
    -2.14
    POSITIVE LOGITS
    <
    3.63
    (
    3.48
    ↵↵
    3.14
    [
    2.94
    ↵
    2.94
     –
    2.91
    –
    2.80
    —
    2.67
    ’
    2.27
     “
    2.25
    Activations Density 0.009%

    No Known Activations