© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99858
    Prev
    Next
    INDEX
    Explanations

    Western Australia locations

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

    The neuron strongly activates on named geographic locations and institutional entities—especially references to Western Australia (place names, organizations, and landmarks).

    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
    oce
    -0.74
     vorticity
    -0.74
     scelto
    -0.69
     Hacienda
    -0.69
    monition
    -0.68
     exposures
    -0.67
     أكبر
    -0.66
    ホンダ
    -0.66
     crucifixion
    -0.66
     Kein
    -0.65
    POSITIVE LOGITS
     Perth
    0.99
     WA
    0.89
    Perth
    0.88
    NEED
    0.85
    WA
    0.84
     Seattle
    0.76
    haga
    0.76
    
    0.76
     Τα
    0.75
    duma
    0.74
    Activations Density 0.023%

    No Known Activations