© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41894
    Prev
    Next
    INDEX
    Explanations

    New York counties and towns

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

    The neuron activates on place names, especially geographic locations (towns, counties, etc.).

    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
    '
    -2.19
     costuras
    -1.90
    
    -1.78
    殽
    -1.75
     xadrez
    -1.69
     geschreven
    -1.63
     bordados
    -1.60
    ᯾
    -1.60
     kleuren
    -1.59
    estos
    -1.59
    POSITIVE LOGITS
    </em>
    2.06
    p
    1.81
     But
    1.79
     Importantly
    1.63
     You
    1.63
    ang
    1.59
    c
    1.59
    蓠
    1.56
     o
    1.53
     但
    1.53
    Activations Density 0.014%

    No Known Activations