© 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. 107950
    Prev
    Next
    INDEX
    Explanations

    Kentucky locations and institutions

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

    The neuron is triggered by numeric tokens (multi‐digit numbers such as counts, dates, monetary amounts, 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
     Tripura
    -0.92
     Lithuania
    -0.82
     Namibia
    -0.81
     Taur
    -0.77
    magne
    -0.77
     Scorpion
    -0.76
     Packer
    -0.74
    CSU
    -0.73
    ignen
    -0.72
    CHLOR
    -0.72
    POSITIVE LOGITS
     Kentucky
    3.19
    Kentucky
    2.97
     Louisville
    2.38
    Louisville
    2.14
     KY
    2.06
     KENT
    1.70
     Lexington
    1.66
     Frankfort
    1.60
     kent
    1.59
     bourbon
    1.58
    Activations Density 0.066%

    No Known Activations