© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42364
    Prev
    Next
    INDEX
    Explanations

    special characters or code blocks

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

    The neuron fires on markup delimiters (e.g. sequences of colons or similar tokens marking block fences or section separators in markdown‐style 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
    ༀ
    -2.95
    ౮
    -2.77
    ⽌
    -2.70
    ⁛
    -2.69
    
    -2.67
    ৢ
    -2.56
    itating
    -2.50
    𐌽
    -2.44
    ſſen
    -2.44
    骉
    -2.39
    POSITIVE LOGITS
     "
    3.28
    ."
    2.77
    ’
    2.64
     entsprechende
    2.59
    -"
    2.48
     offizielle
    2.47
    -
    2.38
     richtige
    2.38
    )
    2.36
     spezielle
    2.31
    Activations Density 0.002%

    No Known Activations