© 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. 72988
    Prev
    Next
    INDEX
    Explanations

    citations and references

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

    The neuron strongly activates on numeric strings that are part of reference or citation details (e.g. volume, issue, page, and year numbers).

    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
     wasn
    -1.09
     Kombat
    -0.92
     here
    -0.90
    ما
    -0.86
     You
    -0.85
    I
    -0.85
     was
    -0.82
     of
    -0.82
     Settembre
    -0.82
    这边
    -0.81
    POSITIVE LOGITS
    的角色
    0.93
    隙
    0.93
    camisa
    0.92
    してます
    0.91
    AllAfrica
    0.90
     лекарства
    0.90
     individuals
    0.89
     producteur
    0.88
    telijke
    0.88
     ongoing
    0.87
    Activations Density 0.006%

    No Known Activations