© 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. 60378
    Prev
    Next
    INDEX
    Explanations

    Copyright, Q, early, many, dumb

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

    The neuron is specialized to pick out software license and copyright boilerplate (e.g. “Copyright,” license terms, version numbers, package and library declarations) from code/document headers.

    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
    assy
    -0.76
    ñoz
    -0.74
     enggak
    -0.73
    RTSN
    -0.73
    electrode
    -0.73
     Ver
    -0.70
     Households
    -0.69
     cabecera
    -0.69
    몬
    -0.69
     Australia
    -0.66
    POSITIVE LOGITS
    Pflege
    0.96
    Hinweis
    0.96
    BMI
    0.94
    Übernach
    0.93
    Aktuelle
    0.93
    Erfahrung
    0.91
    Hinweise
    0.90
     /=
    0.89
    Schritt
    0.89
    SNP
    0.88
    Activations Density 0.004%

    No Known Activations