© 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. 14260
    Prev
    Next
    INDEX
    Explanations

    citrulline, citrate, citruses, citrifolia, citrullinated

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

    the word "cit" followed by letters like "ri", "rate", "rix", or "rull", which appears in technical or scientific text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron responds to any token containing the character sequence “cit.”

    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
    AdvEx
    -2.06
    赑
    -2.06
     citada
    -2.05
     også
    -1.99
    EDING
    -1.95
     */
    -1.92
    あります
    -1.84
     információ
    -1.84
     täglichen
    -1.83
    If
    -1.82
    POSITIVE LOGITS
    癭
    2.44
    翃
    2.39
    剁
    2.31
    ни
    2.28
    隄
    2.19
     ͡
    2.17
    𓐍
    2.05
    ᨆ
    2.00
    и
    2.00
    ꜆
    1.99
    Activations Density 0.002%

    No Known Activations