© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 67512
    Prev
    Next
    INDEX
    Explanations

    ferret tracheal, Notary Public

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

    The neuron fires on standalone nouns naming a class or category (e.g. occupations like “Nanny” or “Notary,” familial roles like “granny,” and species names like “ferret” or “Nannaria”).

    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
     ซึ่ง
    -2.64
    ﻂ
    -2.53
    '
    -2.48
     模様
    -2.44
    乆
    -2.38
     činnosti
    -2.38
     tinged
    -2.33
    </em>
    -2.31
     dobré
    -2.25
     szczegól
    -2.23
    POSITIVE LOGITS
    e
    2.91
     During
    2.44
    Every
    2.42
     To
    2.19
    Both
    2.11
    During
    2.11
    Also
    2.06
    This
    2.05
    <i>
    2.03
    These
    2.03
    Activations Density 0.002%

    No Known Activations