© 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. 128985
    Prev
    Next
    INDEX
    Explanations

    xml and code structures

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

    The neuron strongly activates on numeric tokens (integers or decimals) in structured (XML-like) text.

    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
    饜
    -1.85
     fevere
    -1.75
    一会
    -1.72
    麻煩
    -1.68
     parachoque
    -1.66
     argento
    -1.64
     tramontina
    -1.63
     fhort
    -1.61
     修理
    -1.57
     abiye
    -1.57
    POSITIVE LOGITS
     
    2.08
    wa
    1.85
     is
    1.71
     you
    1.70
     It
    1.67
    _
    1.67
    ↵
    1.66
    in
    1.65
    ícias
    1.65
     tatsäch
    1.63
    Activations Density 0.004%

    No Known Activations