© 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. 10-GEMMASCOPE-RES-131K
    4. 105548
    Prev
    Next
    INDEX
    Explanations

    code keywords and operators

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

    the keyword "else" in programming code.

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

    The neuron is triggered by occurrences of the “else” keyword in code (including preprocessor “#else”).

    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
     vixion
    -1.52
                                
    -1.49
    鹀
    -1.43
     estadounid
    -1.40
    婭
    -1.37
    mediately
    -1.35
    heh
    -1.32
                           
    -1.32
     û
    -1.32
     précie
    -1.31
    POSITIVE LOGITS
     for
    2.22
     with
    1.62
     of
    1.45
    5
    1.42
     to
    1.38
    3
    1.30
    acaktır
    1.23
     if
    1.22
     or
    1.18
     yine
    1.18
    Activations Density 0.001%

    No Known Activations