© 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. 22-GEMMASCOPE-RES-131K
    7. 67583
    Prev
    Next
    INDEX
    Explanations

    citations and scientific sources

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

    scientific citations and company names in academic or scientific texts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on named entities in academic citations—author names, journal titles, databases, and other bibliographic proper nouns.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ÈNE
    -1.24
     obyvateľov
    -1.13
     Fungsi
    -1.13
    RESUMEN
    -1.09
     obrázok
    -1.08
    znych
    -1.08
     هیچ
    -1.08
     menyen
    -1.07
    ᄂ
    -1.05
     が
    -1.02
    POSITIVE LOGITS
     their
    1.39
     these
    1.28
     refer
    1.04
     year
    1.01
     гита
    0.97
     those
    0.97
     particularly
    0.97
     россия
    0.96
     practical
    0.96
     hlavně
    0.95
    Activations Density 0.004%

    No Known Activations