© 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. 59075
    Prev
    Next
    INDEX
    Explanations

    various symbols and punctuation

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

    The neuron activates on programming identifiers used as named parameters or configuration keys (i.e. argument labels) in code.

    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
    鳚
    -1.58
    漚
    -1.55
     médicaments
    -1.52
    _
    -1.47
    becomes
    -1.47
     marchandises
    -1.46
    肮
    -1.46
     péché
    -1.45
    着一个
    -1.42
    鉝
    -1.42
    POSITIVE LOGITS
     majority
    1.57
     we
    1.55
     his
    1.53
     These
    1.52
     However
    1.51
     eccell
    1.48
    や
    1.48
    embley
    1.47
    ',
    1.45
     Hence
    1.45
    Activations Density 0.000%

    No Known Activations