© 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. 22-GEMMASCOPE-RES-131K
    7. 129217
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on occurrences of the place name “Philadelphia.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    Philadelphia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    \
    -1.84
     -
    -1.76
     into
    -1.56
    ("
    -1.44
    —
    -1.38
     görüntüleri
    -1.35
    Z
    -1.33
    mpagne
    -1.30
    9
    -1.30
    8
    -1.30
    POSITIVE LOGITS
     Philadelphia
    1.88
    是怎么回事
    1.79
     Philly
    1.73
     PENNSYLVANIA
    1.66
    ADELPHIA
    1.63
    Philly
    1.61
     Pennsylvania
    1.60
     PHILADELPHIA
    1.57
     elas
    1.52
    Philadelphia
    1.52
    Activations Density 0.064%

    No Known Activations