© 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. 84870
    Prev
    Next
    INDEX
    Explanations

    Copyright and license headers

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

    The neuron fires on comment-style metadata in source files—particularly license/copyright headers and other boilerplate comment lines.

    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
    哂
    -0.84
     disponer
    -0.81
    pelier
    -0.79
    딜
    -0.79
    poses
    -0.78
     Outstanding
    -0.77
     aromatic
    -0.75
    长的
    -0.74
    หน่อย
    -0.74
    setToolTip
    -0.73
    POSITIVE LOGITS
     SAMPLES
    0.77
     Materia
    0.77
     Rude
    0.76
     Solver
    0.74
    ائق
    0.73
     Fors
    0.73
    繼續
    0.71
    枯
    0.71
     UserId
    0.69
     結婚
    0.69
    Activations Density 0.023%

    No Known Activations