© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38629
    Prev
    Next
    INDEX
    Explanations

    thyroid, thylakoid, thyroxine, thymic

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

    words starting with "thy-" related to thyroid, thymus, or thylakoid.

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

    The neuron responds to the character sequence “thy,” i.e. tokens containing that substring (as in thyroid, thymic, thylakoid, etc.).

    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
    鈇
    -4.03
    𖥦
    -3.28
    
    -3.27
    淠
    -3.11
    OUTUBE
    -3.08
    鉺
    -3.03
     parachoque
    -2.98
    怂
    -2.92
    詒
    -2.92
    乆
    -2.91
    POSITIVE LOGITS
    "
    4.03
     You
    3.39
    (
    3.38
    [
    3.08
    \
    3.03
    在
    2.98
    )
    2.94
    It
    2.92
    ',
    2.91
    The
    2.88
    Activations Density 0.007%

    No Known Activations