© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41207
    Prev
    Next
    INDEX
    Explanations

    town and surrounding localities

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

    The neuron activates on the word “town” (especially in phrases like “in town” or “the best in town”).

    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
     “
    -1.61
    すぐに
    -1.59
     niektó
    -1.55
    </h5>
    -1.55
     of
    -1.55
    』、
    -1.55
     animado
    -1.55
     einzigartige
    -1.55
     coreano
    -1.53
    </b>
    -1.52
    POSITIVE LOGITS
    i
    1.87
     These
    1.70
    p
    1.66
     shew
    1.59
     також
    1.55
     Mulher
    1.54
    l
    1.54
    嬗
    1.53
    הס
    1.48
     But
    1.47
    Activations Density 0.005%

    No Known Activations