© 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. 23747
    Prev
    Next
    INDEX
    Explanations

    genomic ancestry

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

    code and programming-related text in technical documentation, especially in a Q&A format.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly fires on numeric and version‐style tokens (e.g. version numbers, build identifiers, large numerals).

    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
    lamb
    -0.73
    catel
    -0.72
    dahl
    -0.72
     skunk
    -0.70
     stickers
    -0.69
    韓国
    -0.68
    ลม
    -0.68
     роди
    -0.68
    loaders
    -0.68
    kolah
    -0.67
    POSITIVE LOGITS
     getLayout
    1.09
     fm
    0.87
     calculation
    0.81
     frigor
    0.75
    یات
    0.74
     FM
    0.73
     paillettes
    0.73
    žné
    0.72
     opponents
    0.71
    
    0.71
    Activations Density 0.017%

    No Known Activations