© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13223
    Prev
    Next
    INDEX
    Explanations

    US state names

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

    This neuron detects the comma in “City, State” place‐name constructs, i.e. it flags the punctuation separating a city name from its state.

    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
     mág
    -1.44
    шивания
    -1.40
     !!!!
    -1.34
     Dinas
    -1.34
     faciliter
    -1.33
     Sistema
    -1.30
     deras
    -1.29
    
    -1.29
    
    -1.29
     continuer
    -1.23
    POSITIVE LOGITS
     which
    1.46
     not
    1.41
     undeniably
    1.38
     markedly
    1.33
     where
    1.32
     profoundly
    1.32
     although
    1.30
     What
    1.30
     During
    1.29
     supremely
    1.28
    Activations Density 0.036%

    No Known Activations