© 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. 34-GEMMASCOPE-RES-131K
    7. 81207
    Prev
    Next
    INDEX
    Explanations

    characterization, tumor, communication

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

    The neuron activates on numeric digits, particularly when they appear in scientific or technical contexts.

    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
    church
    -0.90
    notag
    -0.90
    strual
    -0.85
    
    -0.84
    瞿
    -0.80
    ♾
    -0.79
     nød
    -0.77
    Jahr
    -0.76
    staticmethod
    -0.76
    ioon
    -0.75
    POSITIVE LOGITS
    Outline
    1.36
     Outline
    1.30
     outline
    1.17
     outlines
    0.94
     thanking
    0.88
    まとめ
    0.87
     outlining
    0.87
    contours
    0.87
     flowchart
    0.87
    ﷺ
    0.84
    Activations Density 0.000%

    No Known Activations