© 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. 10-GEMMASCOPE-RES-131K
    7. 111459
    Prev
    Next
    INDEX
    Explanations

    US states and geographical regions

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

    The neuron activates on tokens that are part of geographical place names (cities, states, regions, coasts, 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_10/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
     myös
    -1.49
     również
    -1.34
     also
    -1.33
    際には
    -1.30
     解説
    -1.30
     Those
    -1.29
     גם
    -1.29
    場合には
    -1.27
     When
    -1.27
    起こ
    -1.25
    POSITIVE LOGITS
     onOptions
    1.36
     how
    1.32
    San
    1.26
    ౭
    1.23
    Semitism
    1.20
    Wpf
    1.20
    秾
    1.18
     Dinas
    1.17
     Komis
    1.17
    ER
    1.16
    Activations Density 0.089%

    No Known Activations