© 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. 34-GEMMASCOPE-RES-131K
    7. 98228
    Prev
    Next
    INDEX
    Explanations

    binding

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

    OpenGL and graphics programming related code and API terms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron spotlights programming‐style tokens, especially OpenGL (and related graphics API) function and constant names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Initial
    -0.80
    ٦
    -0.78
    ⁾
    -0.77
    ぷら
    -0.75
    lysses
    -0.75
    thik
    -0.75
    gely
    -0.74
    onyme
    -0.73
     candles
    -0.73
     Ше
    -0.72
    POSITIVE LOGITS
     bind
    1.89
    bind
    1.68
     binding
    1.59
    Bind
    1.52
     binds
    1.50
    绑定
    1.50
     Bind
    1.41
     bound
    1.39
     activate
    1.30
    activate
    1.29
    Activations Density 0.009%

    No Known Activations