© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72801
    Prev
    Next
    INDEX
    Explanations

    Irvine, UCI, Sandman, Ipswich, EGR

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

    This neuron activates on occurrences of the token “Irvine.”

    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
    2
    -4.47
    4
    -4.19
    5
    -4.19
    7
    -4.13
    8
    -4.13
    0
    -4.06
    9
    -3.94
    3
    -3.73
    \
    -3.61
    6
    -3.61
    POSITIVE LOGITS
    砗
    2.89
    鸶
    2.69
    忖
    2.63
    撚
    2.61
    buatan
    2.52
    ceff
    2.50
    獁
    2.50
    ！！”
    2.50
     Universidades
    2.47
    
    2.45
    Activations Density 0.001%

    No Known Activations