© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6861
    Prev
    Next
    INDEX
    Explanations

    graphics shader

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

    The neuron fires on detailed technical troubleshooting language, especially hardware and graphics configuration terms (e.g. GPU models, drivers, reproduction checks).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Blockly
    0.64
    African
    0.59
    ثيل
    0.58
    rigley
    0.58
    🦴
    0.57
     کمر
    0.56
    Posture
    0.56
    JPY
    0.56
     Ansible
    0.55
    🤖
    0.55
    POSITIVE LOGITS
     shader
    1.15
    glGet
    1.14
     GL
    1.11
    glBind
    1.11
    GLuint
    1.09
    GL
    1.08
    gl
    1.05
     Shader
    1.04
     shaders
    1.03
     gl
    1.01
    Activations Density 0.043%

    No Known Activations