© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102634
    Prev
    Next
    INDEX
    Explanations

    conditional compilation directives

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

    C/C++ preprocessor conditionals, especially `#if` statements with logical operators (negation, AND, OR) and platform-specific macros.

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

    This neuron detects C/C++ preprocessor conditional‐compilation directives (e.g. “#if !defined(…)” or related defined/!defined checks).

    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
     it
    -1.62
     when
    -1.51
     メモ
    -1.35
    )=>{
    -1.31
    hogy
    -1.30
     功效
    -1.30
     hered
    -1.29
     asmen
    -1.29
    嗞
    -1.28
     azonban
    -1.27
    POSITIVE LOGITS
     you
    1.57
        
    1.34
    IFICACIÓN
    1.31
    摸了
    1.30
     List
    1.28
     Präsentation
    1.25
    喊道
    1.22
    𐄁
    1.22
     issuance
    1.21
    何故
    1.21
    Activations Density 0.025%

    No Known Activations