© 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. 22-GEMMASCOPE-RES-131K
    7. 72736
    Prev
    Next
    INDEX
    Explanations

    academic citations and publication details

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

    The neuron activates on the numeric and punctuation patterns characteristic of bibliographic citations—volume numbers, page ranges, years, and similar reference 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_22/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
     mouseY
    -0.94
     ",";
    -0.90
     云
    -0.89
    宛
    -0.86
     };
    -0.85
    yttö
    -0.85
    baya
    -0.85
    ével
    -0.84
     ascension
    -0.84
     virulence
    -0.82
    POSITIVE LOGITS
     אחרים
    1.11
     Kondisi
    1.09
    Punkt
    1.06
     taxas
    1.00
    Komentar
    0.96
     заключается
    0.96
    Več
    0.96
    Vlast
    0.96
    kiej
    0.93
    Reak
    0.93
    Activations Density 0.006%

    No Known Activations