© 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. 22-GEMMASCOPE-RES-131K
    7. 67137
    Prev
    Next
    INDEX
    Explanations

    else keyword

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

    The neuron consistently activates on occurrences of the “else” keyword in code.

    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
    趼
    -1.88
    Lä
    -1.49
    iamo
    -1.47
    ıyor
    -1.46
    rée
    -1.40
    нился
    -1.34
     ELECTRO
    -1.33
    읖
    -1.33
    Ꮞ
    -1.33
    Transporte
    -1.30
    POSITIVE LOGITS
     It
    1.34
    {
    1.30
    aliana
    1.29
                
    1.28
            
    1.28
           
    1.21
        
    1.21
     from
    1.20
         
    1.18
     in
    1.17
    Activations Density 0.001%

    No Known Activations