© 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. 45733
    Prev
    Next
    INDEX
    Explanations

    hanging fruit, free software, prior art

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

    The neuron fires on boilerplate free-software license language (e.g. “free software,” “program,” “redistribute,” “license,” etc.).

    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
     数据
    -0.91
    ([],
    -0.75
     creams
    -0.75
     infos
    -0.75
    ຼ
    -0.74
     informations
    -0.74
     الأق
    -0.74
    dataSet
    -0.73
     Lamps
    -0.73
     thingy
    -0.71
    POSITIVE LOGITS
     legislation
    1.72
     footage
    1.59
     scenery
    1.44
     artwork
    1.38
     coursework
    1.34
     machinery
    1.32
     furniture
    1.30
     stuff
    1.27
     material
    1.24
     equipment
    1.23
    Activations Density 0.367%

    No Known Activations