© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 23611
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters

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

    This neuron is keyed to the structural punctuation of metadata or configuration blocks—parentheses, dashes, and especially the equals‐signs used in key–value and attribute assignments.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    urlopen
    -0.81
     DiCaprio
    -0.76
     おしゃれ
    -0.76
     questione
    -0.75
     sababu
    -0.74
    ResponseWriter
    -0.73
     Tissues
    -0.71
     стрем
    -0.71
    React
    -0.71
     Showcase
    -0.71
    POSITIVE LOGITS
     *.
    1.34
    *.
    1.31
    ^.
    1.16
     "*.
    1.04
    +.
    1.03
    **.
    1.02
    ~.
    0.99
    [.
    0.97
    _.
    0.94
     +.
    0.87
    Activations Density 0.086%

    No Known Activations