© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104219
    Prev
    Next
    INDEX
    Explanations

    academic citations

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

    The neuron detects in‐text citation or reference markers (e.g., the bracketed “[@…]” tokens).

    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
    ))))
    -2.02
    llten
    -1.98
    replyreport
    -1.95
     says
    -1.92
     gets
    -1.91
    ogonal
    -1.84
    opardy
    -1.84
    ();
    -1.79
     яку
    -1.77
    ....
    -1.77
    POSITIVE LOGITS
     Krzysz
    2.11
     burbu
    1.99
     essayer
    1.93
     luminoso
    1.90
     toen
    1.90
    ágenes
    1.89
     czarny
    1.87
     navide
    1.86
     Unii
    1.84
     unie
    1.84
    Activations Density 0.065%

    No Known Activations