© 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. 60672
    Prev
    Next
    INDEX
    Explanations

    word-ending punctuation, common words, numbers

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

    The neuron fires strongly on tokens that occur in software license or copyright header comment blocks.

    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
    yed
    -0.83
    КЕ
    -0.77
    khar
    -0.75
    IRED
    -0.75
    }.
    -0.75
    jados
    -0.72
    ৱ
    -0.72
    defined
    -0.72
     товаров
    -0.72
    moll
    -0.72
    POSITIVE LOGITS
    西装
    0.71
     temperaturas
    0.71
     പ്ര
    0.71
     chiếm
    0.69
    ош
    0.68
    四季
    0.68
     mutat
    0.68
     Metallurgy
    0.67
    襄
    0.66
     chắc
    0.66
    Activations Density 0.007%

    No Known Activations