© 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. 2630
    Prev
    Next
    INDEX
    Explanations

    academic journal publishers

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

    The neuron detects bibliographic‐metadata tokens in academic article headers—labels like “Publisher,” dates, colons, URLs, journal‐name bits, and related numeric or punctuation markers.

    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
     ISBN
    -0.85
    vábbi
    -0.79
    crtc
    -0.75
    注入
    -0.74
     sud
    -0.73
    気に
    -0.72
    ciorys
    -0.72
    زندگی
    -0.71
     зар
    -0.71
    ARIOS
    -0.71
    POSITIVE LOGITS
     journals
    1.99
     journal
    1.96
     Journals
    1.85
     Elsevier
    1.59
    journals
    1.57
     Springer
    1.56
     Wiley
    1.48
     publisher
    1.34
    Wiley
    1.30
     Journal
    1.30
    Activations Density 0.057%

    No Known Activations