© 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. 102766
    Prev
    Next
    INDEX
    Explanations

    Western Australia locations

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

    The neuron fires on geographic proper names—especially place names (like suburbs, districts, regions, etc.) in Western Australia.

    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
    lerini
    -0.79
     Pietro
    -0.70
     SCM
    -0.66
    Carcinogenicity
    -0.66
    ߙ
    -0.66
    Palm
    -0.66
     Ved
    -0.66
     тренер
    -0.65
     Dudley
    -0.65
    Long
    -0.63
    POSITIVE LOGITS
    literally
    0.76
    everybody
    0.72
     creadores
    0.70
    ализация
    0.70
     weib
    0.70
    niak
    0.70
    officially
    0.70
    ipu
    0.69
    στη
    0.69
    abil
    0.69
    Activations Density 0.032%

    No Known Activations