© 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. 70493
    Prev
    Next
    INDEX
    Explanations

    code artifacts and types

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

    The neuron activates on literal strings that look like code import paths or file‐system paths (e.g. “github.com/...”, “google.golang.org/...”, “requirements.txt”, “__init__.py”).

    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
    endfor
    -1.07
     so
    -0.94
    ="
    -0.94
    ())
    
    -0.93
    %).
    -0.90
    》.
    -0.90
    :"
    -0.88
     Bacteriol
    -0.88
    )。
    -0.87
    ;
    
    
    -0.87
    POSITIVE LOGITS
     Além
    0.98
     좋
    0.96
     happ
    0.96
    Carex
    0.94
    Antal
    0.93
     Avid
    0.92
    norme
    0.92
     Algunas
    0.91
    angerschaft
    0.91
     nhắn
    0.91
    Activations Density 0.060%

    No Known Activations