© 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. 92457
    Prev
    Next
    INDEX
    Explanations

    category labels

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

    The neuron detects license-header boilerplate in code comments (e.g. Apache License disclaimers and their formatting markers).

    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
    jasama
    -0.81
    ikaze
    -0.79
     փ
    -0.77
    ؍
    -0.77
     pessimism
    -0.77
     svårt
    -0.76
    endiendo
    -0.75
    قلال
    -0.75
    nambuco
    -0.74
     seriousness
    -0.73
    POSITIVE LOGITS
    empres
    0.79
    ELEMENT
    0.78
    ¹
    0.73
    亮
    0.73
    ®
    0.72
     کیلوم
    0.72
     eternal
    0.72
    anat
    0.71
    ės
    0.71
     Barrie
    0.71
    Activations Density 0.001%

    No Known Activations