© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 76448
    Prev
    Next
    INDEX
    Explanations

    license or copyright

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

    The neuron detects legal or patent‐style boilerplate phrases, especially references to “those skilled in the art” and licensing/disclaimer language.

    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
     community
    -0.79
     бу
    -0.73
    下一个
    -0.68
     UT
    -0.67
    ツー
    -0.64
    Hermann
    -0.64
     Kingdom
    -0.64
     state
    -0.63
     Hermann
    -0.62
     stakes
    -0.62
    POSITIVE LOGITS
    ⣠
    0.74
     Changer
    0.73
    Seb
    0.73
    zim
    0.71
     Seb
    0.69
    sealed
    0.68
    actéristique
    0.68
     kuro
    0.68
     legato
    0.68
    ilación
    0.67
    Activations Density 0.066%

    No Known Activations