© 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. 34-GEMMASCOPE-RES-131K
    7. 99452
    Prev
    Next
    INDEX
    Explanations

    streets and districts

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

    The neuron fires strongly on numeric tokens and address markers (e.g. street numbers, ordinals, and related prepositions), effectively identifying street‐address or location indicators.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Palazzo
    -0.84
    savevideo
    -0.84
     custodia
    -0.81
     spatial
    -0.81
    萼
    -0.80
    Ɨ
    -0.80
    etsch
    -0.80
    geometric
    -0.79
     enfermera
    -0.79
     apartments
    -0.79
    POSITIVE LOGITS
     Main
    1.02
     trendy
    0.98
     strip
    0.95
     promenade
    0.93
     Avenue
    0.91
     Broadway
    0.90
     shopping
    0.89
     lively
    0.88
     main
    0.87
     Miracle
    0.85
    Activations Density 0.041%

    No Known Activations