© 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. 9382
    Prev
    Next
    INDEX
    Explanations

    Kansas City, Kansas highway

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

    The neuron activates on mentions of “Kansas” (and related Kansas place names like Kansas City or Lawrence).

    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
    ’
    -1.59
     amargo
    -1.41
    ますが
    -1.35
     měl
    -1.34
    </i>
    -1.34
     flourish
    -1.30
     fastening
    -1.27
     Якщо
    -1.25
     the
    -1.22
    rashed
    -1.22
    POSITIVE LOGITS
    Kansas
    2.08
     Kansas
    1.77
    Oklahoma
    1.66
     Oklahoma
    1.52
     Missouri
    1.52
     Anything
    1.51
     Omaha
    1.48
     It
    1.48
     KC
    1.48
     ALS
    1.47
    Activations Density 0.032%

    No Known Activations