© 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. 10-GEMMASCOPE-RES-131K
    7. 100198
    Prev
    Next
    INDEX
    Explanations

    city names and locations

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

    The neuron detects mentions of geographical locations or place names (e.g., cities, neighborhoods, malls, communities).

    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
     against
    -1.21
     more
    -1.20
    cows
    -1.17
     previously
    -1.16
     that
    -1.13
    EdgeInsets
    -1.12
     until
    -1.10
    蒾
    -1.10
     a
    -1.09
     another
    -1.09
    POSITIVE LOGITS
     these
    1.23
    讪
    1.20
     solchen
    1.20
     you
    1.14
     voici
    1.13
     tolerably
    1.10
    月は
    1.10
    edakan
    1.09
     furent
    1.08
    隸
    1.08
    Activations Density 0.089%

    No Known Activations