© 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. 73696
    Prev
    Next
    INDEX
    Explanations

    Salford, Cheshire, Manchester

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

    The neuron flags mentions of geographic place names (towns, cities, regions).

    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
    ют
    -1.56
     wesentlichen
    -1.39
    IVERSITY
    -1.36
     ferons
    -1.34
     accordance
    -1.30
     libere
    -1.29
     Никола
    -1.27
    geh
    -1.23
     resultaten
    -1.23
    क्टर
    -1.22
    POSITIVE LOGITS
     PEG
    1.45
     you
    1.43
     bene
    1.41
    .--
    1.35
     has
    1.35
    ?"
    1.34
    ",
    1.32
    ’
    1.27
    hubung
    1.26
    '
    1.26
    Activations Density 0.016%

    No Known Activations