© 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. 10-GEMMASCOPE-RES-131K
    7. 85608
    Prev
    Next
    INDEX
    Explanations

    US Universities and states

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

    The neuron fires on capitalized geographic or institutional names—especially U.S. states and “State”–based universities/counties.

    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
    謌
    -2.52
    すっ
    -2.38
    お互
    -2.14
    
    -2.13
     mães
    -2.13
     prenant
    -2.11
    なるべく
    -2.11
     теми
    -2.09
     the
    -2.08
    今も
    -2.08
    POSITIVE LOGITS
    ?”
    2.39
    Однако
    2.36
     {
    2.30
    ”،
    2.16
    珦
    2.14
    ！”
    2.11
     has
    2.08
     nova
    2.06
    橚
    2.05
    That
    2.03
    Activations Density 0.005%

    No Known Activations