© 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. 38528
    Prev
    Next
    INDEX
    Explanations

    street names and locations

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

    The neuron fires on occurrences of “Main Street” (and its abbreviated forms like “Main St”) or numeric addresses on Main Street.

    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
     única
    -1.77
     único
    -1.73
     antemano
    -1.73
     Bedingungen
    -1.73
     you
    -1.68
     Monaten
    -1.67
    .
    -1.65
    afficher
    -1.63
     Umständen
    -1.59
     Bedürfn
    -1.58
    POSITIVE LOGITS
    ༀ
    1.89
    na
    1.89
    梣
    1.89
    .}(
    1.83
    ]}\
    1.78
    ௅
    1.74
     培训
    1.71
    +}\
    1.70
    刧
    1.70
    ⪧
    1.66
    Activations Density 0.004%

    No Known Activations