© 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. 22-GEMMASCOPE-RES-131K
    7. 72522
    Prev
    Next
    INDEX
    Explanations

    Baltimore, Maryland

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

    This neuron activates on mentions of the city “Baltimore” (and related Maryland place names) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    .
    -1.43
    榈
    -1.39
    東西
    -1.39
     lateinit
    -1.35
    に興味
    -1.35
     Ciencia
    -1.34
    調節
    -1.34
     Ingeniería
    -1.34
     Enfer
    -1.33
    *}[
    -1.32
    POSITIVE LOGITS
    '
    2.00
     Maryland
    1.93
     två
    1.83
    Maryland
    1.63
     Baltimore
    1.63
    ↵
    1.63
    も
    1.39
     zweier
    1.38
    なので
    1.30
    şekkür
    1.28
    Activations Density 0.034%

    No Known Activations