© 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. 10-GEMMASCOPE-RES-131K
    7. 90599
    Prev
    Next
    INDEX
    Explanations

    code-related keywords

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

    The neuron primarily detects numeric literals (especially floating-point numbers) in code or data snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     possibly
    -1.87
     various
    -1.83
     some
    -1.75
    0
    -1.70
     more
    -1.69
    Even
    -1.68
     sometimes
    -1.63
     even
    -1.63
     an
    -1.58
     potentially
    -1.52
    POSITIVE LOGITS
     mauva
    1.75
    "",
    1.71
     auffi
    1.65
    䛗
    1.60
     från
    1.60
     kaffe
    1.59
     GOtt
    1.59
     eſſ
    1.59
    
    1.56
    makeat
    1.55
    Activations Density 0.227%

    No Known Activations