© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 83649
    Prev
    Next
    INDEX
    Explanations

    Fort Worth, Texas

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

    The neuron strongly activates on proper-name tokens related to Fort Worth (e.g. “Fort Worth,” “TCU,” “Texas Christian University”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ↵
    -2.56
    罴
    -2.38
    
    -2.06
    ところは
    -2.05
    どうして
    -2.03
    どうやって
    -2.03
    悩む
    -2.02
    他們的
    -1.98
     jesteśmy
    -1.98
    ꔛ
    -1.96
    POSITIVE LOGITS
    '
    2.55
    ｙ
    2.25
    })=\
    2.08
    на
    1.95
    躥
    1.82
    踽
    1.77
    ！！”
    1.75
    的
    1.74
    It
    1.73
    行
    1.73
    Activations Density 0.004%

    No Known Activations