© 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. 22-GEMMASCOPE-RES-131K
    4. 68882
    Prev
    Next
    INDEX
    Explanations

    code and punctuation

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

    The neuron fires on programming‐style code tokens—especially CamelCase or PascalCase identifiers and other code syntax—marking blocks of source code rather than natural language.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     this
    -1.75
     very
    -1.21
     данном
    -1.20
     for
    -1.20
     despite
    -1.20
     дії
    -1.19
     volunteering
    -1.16
     displayed
    -1.15
     Padding
    -1.15
     previous
    -1.14
    POSITIVE LOGITS
     ",";
    1.61
    virano
    1.46
    ┍
    1.45
    Preparazione
    1.45
     asesinado
    1.45
     reflexiones
    1.45
     ejerc
    1.44
     zimní
    1.38
    がありますが
    1.34
     sugerencias
    1.34
    Activations Density 0.001%

    No Known Activations