© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1699
    Prev
    Next
    INDEX
    Explanations

    critical pedagogy praxis Freire

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

    This neuron specializes in spotting bibliographic reference elements—author names, publication titles, volume/issue markers, page numbers, and similar citation metadata.

    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
    ridas
    -0.82
     margiela
    -0.81
    strncmp
    -0.78
     fikir
    -0.76
     Lombardi
    -0.75
    arching
    -0.75
    で大
    -0.73
    Ƚ
    -0.73
     trânsito
    -0.73
    hidup
    -0.73
    POSITIVE LOGITS
     Freire
    1.47
     Paulo
    1.34
    Paulo
    1.32
     Pedagog
    1.20
     conscienti
    1.17
     pedagogy
    1.16
     Praxis
    1.01
    Pedagog
    1.01
     critical
    1.00
     praxis
    0.98
    Activations Density 0.024%

    No Known Activations