© 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. 34-GEMMASCOPE-RES-131K
    4. 92378
    Prev
    Next
    INDEX
    Explanations

    local government districts and councils

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

    The neuron fires strongly on multi‐token capitalized spans naming places, councils, constituencies, and other proper‐noun organizations.

    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
    itahu
    -0.85
    ℘
    -0.82
     kekerasan
    -0.75
    IAI
    -0.74
    commodity
    -0.73
     COUNTY
    -0.72
     приез
    -0.71
     ||
    
    -0.71
    '])
    
    -0.70
    AUTHENT
    -0.70
    POSITIVE LOGITS
     District
    1.19
     district
    1.18
     Council
    1.10
     council
    1.09
    District
    1.00
    rict
    0.99
     borough
    0.97
    Council
    0.92
    district
    0.84
     unitary
    0.84
    Activations Density 0.027%

    No Known Activations