© 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. 10-GEMMASCOPE-RES-131K
    7. 65891
    Prev
    Next
    INDEX
    Explanations

    street names and places

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

    The neuron detects the proper nouns that name streets, avenues, districts, and other geographic or address elements.

    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
     rempliss
    -1.58
     still
    -1.45
    ).
    -1.41
     cœurs
    -1.31
     megfelelő
    -1.31
    ",
    -1.30
     dlaczego
    -1.30
    resten
    -1.29
     udało
    -1.28
    westen
    -1.26
    POSITIVE LOGITS
     on
    1.68
     to
    1.54
     by
    1.41
     plati
    1.30
     perdagangan
    1.29
     serupa
    1.29
     at
    1.20
     berlina
    1.19
     medesimo
    1.18
     Finlandia
    1.16
    Activations Density 0.145%

    No Known Activations