© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106642
    Prev
    Next
    INDEX
    Explanations

    Saratoga Springs

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

    The neuron activates strongly on place names—especially local geographic locations (towns, venues, etc.).

    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
    assed
    -0.75
     Requests
    -0.73
    Editar
    -0.73
    出場
    -0.69
    requests
    -0.68
     floors
    -0.68
    둔
    -0.68
    elde
    -0.67
     étages
    -0.66
     liver
    -0.66
    POSITIVE LOGITS
     Saratoga
    1.39
     Adirond
    1.13
     Schenectady
    0.87
     ANZ
    0.85
     Skid
    0.84
     SUNY
    0.83
     vl
    0.82
     Wilton
    0.80
    ANZ
    0.79
     SIT
    0.76
    Activations Density 0.011%

    No Known Activations