© 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. 22-GEMMASCOPE-RES-131K
    7. 130347
    Prev
    Next
    INDEX
    Explanations

    This neuron detects formal section‐heading phrases in technical or academic documents—especially “Literature Review,” “Related Art,” or similar.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    related art and literature review

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     circunstan
    -1.11
     berlaku
    -1.08
    viembre
    -1.08
    濺
    -1.07
     יְ
    -1.06
    Mål
    -1.05
     after
    -1.05
     when
    -1.03
    Ār
    -1.03
     porcentual
    -1.01
    POSITIVE LOGITS
     research
    1.73
     relevant
    1.50
     existing
    1.24
     literature
    1.19
     saveurs
    1.17
     relevante
    1.15
    relevant
    1.13
     related
    1.13
     البحث
    1.12
    Relevant
    1.09
    Activations Density 0.174%

    No Known Activations