© 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. 57813
    Prev
    Next
    INDEX
    Explanations

    research paper findings

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

    This neuron detects academic writing, particularly when authors present their research papers or studies.

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

    The neuron detects academic self-references and discourse markers typical of research papers (e.g. “this paper,” “by reviewing,” “we …”).

    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
    报表
    -0.80
    itory
    -0.79
     Ske
    -0.77
    Caution
    -0.77
     однако
    -0.75
     UNO
    -0.74
     Lamp
    -0.74
    caution
    -0.73
    امل
    -0.71
     leh
    -0.71
    POSITIVE LOGITS
     analysis
    0.92
     mojej
    0.90
    introdu
    0.86
     Manfaat
    0.86
     cioccolato
    0.84
     pointed
    0.84
    分析
    0.84
     further
    0.84
     schermo
    0.83
     commercio
    0.82
    Activations Density 0.099%

    No Known Activations