© 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. 20818
    Prev
    Next
    INDEX
    Explanations

    Princeton entities

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

    The neuron strongly activates on occurrences of the token “Princeton,” i.e. mentions of Princeton (usually as part of “Princeton University” or related references).

    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
    e
    -3.56
    </strong>
    -3.02
    u
    -2.48
    </u>
    -2.47
    는
    -2.39
     we
    -2.34
    ...?
    -2.31
    は
    -2.30
    </h1>
    -2.28
     l
    -2.28
    POSITIVE LOGITS
    嵎
    2.89
    းက
    2.42
     attentive
    2.31
    
    2.28
     选
    2.28
    鯓
    2.27
     rígida
    2.23
    uillez
    2.23
     戰
    2.23
    婓
    2.20
    Activations Density 0.005%

    No Known Activations