© 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. 67461
    Prev
    Next
    INDEX
    Explanations

    citation markers like [@B]

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

    The neuron fires on in‐text citation or reference markers (e.g. bracketed or “@”–style bibliographic references).

    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
     -
    -2.06
    m
    -2.03
    ....
    -1.91
     '
    -1.88
    l
    -1.80
    !!
    -1.80
    .....
    -1.78
    a
    -1.73
    !!!
    -1.73
    ......
    -1.72
    POSITIVE LOGITS
    詎
    2.02
    鹋
    1.90
    linawan
    1.85
    蜴
    1.81
    棡
    1.73
    excuse
    1.70
     帅气
    1.69
    Bulgaria
    1.69
    🫴
    1.69
     Reglas
    1.68
    Activations Density 0.002%

    No Known Activations