© 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. 34-GEMMASCOPE-RES-131K
    7. 2250
    Prev
    Next
    INDEX
    Explanations

    bib files and citation styles

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

    The neuron detects section headings or markers that introduce bibliographies or reference lists (e.g. “bibliography:”, “references”, “bib…”).

    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
    kton
    -0.85
     PIX
    -0.81
     Gom
    -0.79
    哝
    -0.78
     Cama
    -0.78
     resize
    -0.77
     commiss
    -0.77
    ropia
    -0.77
     Pix
    -0.76
     Probes
    -0.76
    POSITIVE LOGITS
     citation
    1.51
     cite
    1.27
    Cite
    1.20
     citing
    1.20
     Cite
    1.16
    Citation
    1.08
     citations
    1.05
    citation
    1.05
     Citation
    1.04
     bibliographies
    1.03
    Activations Density 0.073%

    No Known Activations