© 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. 58362
    Prev
    Next
    INDEX
    Explanations

    substrate binding and specificity

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

    The neuron detects the word "substrate" and related biochemical terminology in scientific contexts.

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

    The neuron specifically fires on occurrences of the word “substrate” (and its variants) in the biological/scientific text.

    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
    an
    -2.83
    is
    -2.78
    of
    -2.50
    ties
    -2.45
    _
    -2.31
    ala
    -2.28
    谖
    -2.22
    y
    -2.20
    ito
    -2.19
    or
    -2.17
    POSITIVE LOGITS
    OUTUBE
    2.45
    aphne
    2.33
     сестра
    2.25
     citado
    2.22
    \
    2.19
     vollständ
    2.17
    錞
    2.17
    狆
    2.14
     Según
    2.13
    霂
    2.13
    Activations Density 0.014%

    No Known Activations