© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73686
    Prev
    Next
    INDEX
    Explanations

    Indiana and Indianapolis

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

    The neuron strongly activates on the word “Indiana,” especially when it appears in official names or place references.

    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
    m
    -1.66
    f
    -1.66
    b
    -1.59
     in
    -1.55
     from
    -1.53
     or
    -1.51
    g
    -1.49
    c
    -1.46
    u
    -1.41
     ellas
    -1.38
    POSITIVE LOGITS
    ⩤
    1.48
    嵓
    1.43
    ሖ
    1.41
    dzić
    1.40
    Dış
    1.35
    ugais
    1.34
     Affaires
    1.34
    eload
    1.34
     provocando
    1.34
    沨
    1.33
    Activations Density 0.052%

    No Known Activations