© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111691
    Prev
    Next
    INDEX
    Explanations

    code structure and text formatting

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

    tokens related to data types, formats, and technical specifications in code and configuration files.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on occurrences of the substring “text” in identifiers, filenames, or MIME types.

    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
        
    -1.86
      
    -1.76
    (
    -1.64
    s
    -1.59
    ↵↵
    -1.59
    𝐃
    -1.59
    iços
    -1.59
    THEY
    -1.57
    OUR
    -1.55
     whoſe
    -1.55
    POSITIVE LOGITS
     the
    2.23
    ظمة
    2.08
     nasz
    2.02
    ONESIA
    1.88
     często
    1.83
     sabias
    1.83
    sonaro
    1.82
     amounts
    1.81
     continúas
    1.80
     diariamente
    1.79
    Activations Density 0.060%

    No Known Activations