© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30725
    Prev
    Next
    INDEX
    Explanations

    introduction

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

    This neuron detects structural metadata and section headings in academic papers—tokens like “author,” “Introduction,” volume/number labels, DOI digits, etc.

    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
    ющи
    -0.82
    lowe
    -0.75
     Auctions
    -0.73
    lles
    -0.73
     vz
    -0.72
    вос
    -0.72
     Bashir
    -0.71
    couldn
    -0.70
    cetos
    -0.69
     blanches
    -0.69
    POSITIVE LOGITS
    aylor
    0.81
     AMS
    0.75
    ぎ
    0.74
     obcí
    0.72
     deus
    0.71
    MOL
    0.71
    elfde
    0.70
    稱為
    0.70
     البحث
    0.70
    BUL
    0.70
    Activations Density 0.002%

    No Known Activations