© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60651
    Prev
    Next
    INDEX
    Explanations

    Milwaukee entities and HTC products

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

    This neuron responds to capitalized tokens containing a double-letter sequence (e.g. “Torres” with “rr” or “Milwaukee” with “ee”).

    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
    *
    -3.08
    /
    -3.02
    `
    -2.66
    {
    -2.50
    ."
    -2.45
    ]
    -2.42
    [
    -2.38
    U
    -2.38
     jokingly
    -2.34
    <
    -2.34
    POSITIVE LOGITS
     reconocidos
    2.39
    祧
    2.33
     parecen
    2.28
    ે
    2.27
    臜
    2.25
    のかもしれません
    2.16
    踽
    2.14
    砗
    2.13
    茕
    2.09
    笵
    2.09
    Activations Density 0.008%

    No Known Activations