© 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. 21348
    Prev
    Next
    INDEX
    Explanations

    Katrina, Belinda, RFID

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

    The neuron fires on domain‐specific proper nouns and acronyms—e.g. names like “Katrina,” “Belinda,” “Kruger” and technical all‐caps tokens like “RFID.”

    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
    \
    -3.20
    In
    -3.08
    >
    -2.88
    珦
    -2.75
    This
    -2.66
    replyreport
    -2.64
    т
    -2.59
    뿍
    -2.58
    It
    -2.56
     Determining
    -2.55
    POSITIVE LOGITS
    e
    2.61
     dão
    2.27
     Vereinbarung
    2.27
    狁
    2.22
     estadía
    2.19
     encontram
    2.16
     dijeron
    2.14
     lw
    2.13
    of
    2.09
    があって
    2.09
    Activations Density 0.014%

    No Known Activations