© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 123696
    Prev
    Next
    INDEX
    Explanations

    preprocessor directive defines

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

    C/C++ preprocessor macro definitions, particularly the opening parenthesis and parameters following `#define`.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    ︲
    -1.23
     colega
    -1.22
     infância
    -1.17
    を開
    -1.15
     assuring
    -1.14
     pittore
    -1.14
     conozco
    -1.13
     نحن
    -1.12
     urgencia
    -1.11
    tanto
    -1.09
    POSITIVE LOGITS
     plutôt
    1.37
     berwarna
    1.23
     televiz
    1.22
     herself
    1.21
     actions
    1.16
     nuevamente
    1.15
     kiri
    1.12
     kembali
    1.10
    ANCHE
    1.09
     himself
    1.07
    Activations Density 0.036%

    No Known Activations