© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 100046
    Prev
    Next
    INDEX
    Explanations

    freeglut and GLFW initialization

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

    references to GLUT and GLFW graphics library functions and identifiers in programming code.

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

    The neuron fires on OpenGL‐related library or API names (e.g. GLUT, GLFW, 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_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
    );
    -1.66
    )?
    -1.59
    ))
    -1.52
    ).
    -1.45
     Unless
    -1.41
     is
    -1.38
    /');
    -1.34
    ):
    -1.34
    有三
    -1.34
    )),
    -1.33
    POSITIVE LOGITS
     autres
    1.59
    鱨
    1.47
    Converters
    1.45
     gondol
    1.44
     vraiment
    1.41
     доставка
    1.41
     quieren
    1.41
     knihy
    1.40
    满脸
    1.38
    豳
    1.38
    Activations Density 0.010%

    No Known Activations