© 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. 34-GEMMASCOPE-RES-131K
    7. 57764
    Prev
    Next
    INDEX
    Explanations

    download online videos

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

    This neuron strongly activates on programming-style punctuation and delimiters—e.g. parentheses, quotes, brackets, and other code-syntax tokens.

    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
     visto
    -0.81
     public
    -0.80
     transverse
    -0.78
     tengo
    -0.77
     литературы
    -0.76
     shape
    -0.75
     среды
    -0.75
     рам
    -0.73
    Repository
    -0.73
    効果
    -0.73
    POSITIVE LOGITS
     kwaliteit
    0.98
     DASH
    0.94
     quality
    0.88
    Vídeo
    0.85
     качество
    0.85
     Butterflies
    0.84
    Качество
    0.84
    itag
    0.84
    Abraham
    0.84
     ποι
    0.79
    Activations Density 0.017%

    No Known Activations