© 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. 22-GEMMASCOPE-RES-131K
    7. 35101
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation

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

    The neuron activates on tokens representing punctuation characters or their names (e.g. space, slash/backslash, quotes, double‐colon).

    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
    でもあります
    -1.03
    ViewChild
    -1.00
    ácie
    -0.98
     搞笑
    -0.98
    でもある
    -0.96
     crochê
    -0.96
    Ohne
    -0.95
    衬衫
    -0.94
    tismo
    -0.94
    volves
    -0.94
    POSITIVE LOGITS
     in
    1.88
     on
    1.18
     framför
    1.15
     over
    0.97
    美味しく
    0.94
     grammatical
    0.93
     for
    0.93
     between
    0.93
     beschä
    0.93
     increase
    0.92
    Activations Density 0.084%

    No Known Activations