© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57143
    Prev
    Next
    INDEX
    Explanations

    software licenses

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

    The neuron detects references to open-source license URLs (e.g., “http://opensource.org/licenses/…”).

    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
    putBoolean
    -0.95
    函数
    -0.92
    은
    -0.86
    ⌀
    -0.86
    チ
    -0.85
    letti
    -0.84
    ๑
    -0.84
     but
    -0.81
    <i>
    -0.81
    ͑
    -0.81
    POSITIVE LOGITS
    LICENSE
    1.00
    licenses
    0.92
    gratis
    0.88
     enfance
    0.88
    gunaan
    0.87
    highlights
    0.86
     立体
    0.86
    Aplica
    0.86
    nước
    0.84
    karakter
    0.84
    Activations Density 0.165%

    No Known Activations