© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 33129
    Prev
    Next
    INDEX
    Explanations

    locations and directions

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

    The neuron strongly activates on tokens that are part of place names or geographic locations.

    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
     Island
    -0.96
     island
    -0.93
    Island
    -0.91
     islands
    -0.91
     Islands
    -0.91
     富士
    -0.87
    کیل
    -0.82
     Bermuda
    -0.81
    cheap
    -0.78
    cfg
    -0.77
    POSITIVE LOGITS
     remote
    0.84
    ніципалі
    0.81
     lighthouse
    0.80
     alienated
    0.75
     geno
    0.75
    VENDOR
    0.74
    topRight
    0.74
     północ
    0.74
    NORTH
    0.73
     pristine
    0.73
    Activations Density 0.061%

    No Known Activations