© 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. 12662
    Prev
    Next
    INDEX
    Explanations

    England and Wales

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

    The neuron specializes in detecting the place name “Wales” (and its adjectival form “Welsh”).

    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
    ஂ
    -2.84
    笮
    -2.73
    \
    -2.73
    d
    -2.70
    t
    -2.58
    ins
    -2.44
    
    -2.36
    昞
    -2.33
    '
    -2.27
     is
    -2.25
    POSITIVE LOGITS
    penes
    2.36
     entsprechende
    2.27
     ocorrer
    2.16
    但
    2.13
    lgari
    2.13
    .“
    2.11
    如果
    2.08
    ruzzo
    2.06
     desempen
    2.03
    ſu
    2.03
    Activations Density 0.005%

    No Known Activations