© 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. 10-GEMMASCOPE-RES-131K
    7. 59342
    Prev
    Next
    INDEX
    Explanations

    review citations

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

    The neuron detects academic citation markers and reference phrases (e.g. “for reviews, see … [#]”) in scholarly text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     not
    -1.77
     just
    -1.45
    izes
    -1.26
     along
    -1.23
     like
    -1.23
     alongside
    -1.23
     famosa
    -1.20
     your
    -1.19
     with
    -1.19
    沐浴
    -1.16
    POSITIVE LOGITS
     but
    1.86
    return
    1.57
     Países
    1.45
     médio
    1.38
     cependant
    1.38
     Acerca
    1.38
     Publicar
    1.31
    AFTER
    1.30
     اینجا
    1.27
     ولكن
    1.26
    Activations Density 0.040%

    No Known Activations