© 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. 95740
    Prev
    Next
    INDEX
    Explanations

    build system configuration files

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

    The neuron fires on mentions of build‐automation tools or build script filenames (e.g. Rake, Makefile, CMake, Ant, etc.).

    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
    ');
    -1.13
     educativas
    -1.10
    ód
    -1.04
    );
    -1.02
    [];
    
    -1.00
    three
    -0.99
    ുള്ള
    -0.99
    hrten
    -0.97
     mostrarán
    -0.96
    
    -0.96
    POSITIVE LOGITS
    corbic
    1.25
    pergillus
    1.18
     стене
    1.16
     budete
    1.12
     script
    1.04
     tranquilo
    1.00
    aget
    1.00
     የ
    1.00
     process
    1.00
    謳
    0.99
    Activations Density 0.130%

    No Known Activations