© 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. 38253
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms

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

    This neuron activates on closing punctuation, particularly at the end of sentences and code blocks.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    轰隆
    -0.95
     Victorian
    -0.89
    星人
    -0.88
     スイーツ
    -0.88
    Bandit
    -0.85
    Comentários
    -0.84
    ліки
    -0.84
     irritation
    -0.84
    suites
    -0.83
    adecimal
    -0.82
    POSITIVE LOGITS
     thousands
    1.13
     clinica
    0.97
     antibio
    0.94
     marea
    0.93
     hund
    0.91
    !!</
    0.91
     surfact
    0.91
     wherever
    0.90
     dinosau
    0.88
     thermomix
    0.88
    Activations Density 0.002%

    No Known Activations