© 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. 34-GEMMASCOPE-RES-131K
    7. 32181
    Prev
    Next
    INDEX
    Explanations

    journal names and scientific terms

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

    academic journal citations and references in scientific texts.

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

    The neuron fires on bibliographic and citation material (journal titles, volume/page numbers, years, section headings, and other reference metadata).

    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
    バット
    -0.85
    🔥🔥
    -0.82
    XJ
    -0.82
    🙄
    -0.81
     violenza
    -0.81
    /*.
    -0.80
    🤢
    -0.80
     engin
    -0.79
    🥲
    -0.79
     península
    -0.78
    POSITIVE LOGITS
     Nature
    1.25
     Natur
    1.02
     nature
    1.00
    Nature
    0.93
     Royal
    0.82
     Polar
    0.82
     Exercise
    0.80
     naturaleza
    0.80
     plo
    0.80
     Current
    0.79
    Activations Density 0.041%

    No Known Activations