© 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. 128554
    Prev
    Next
    INDEX
    Explanations

    bisphenol A, homocysteine, babymetal

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

    chemical and biochemical compound names.

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

    The neuron is strongly activated by multi‐syllabic chemical and biochemical substance names (e.g. Bisphenol A/BPA, pellagra, homocysteine, 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
     and
    -1.78
    </em>
    -1.60
     kilku
    -1.59
     "
    -1.59
     zarówno
    -1.53
     สำหรับ
    -1.52
    </b>
    -1.51
     другими
    -1.48
     innych
    -1.48
    ).
    -1.48
    POSITIVE LOGITS
    izacji
    1.50
    而
    1.43
    &:
    1.39
    cjach
    1.39
     wasn
    1.35
    ですし
    1.34
    <0xF0>
    1.34
     må
    1.31
    āja
    1.31
     Before
    1.30
    Activations Density 0.081%

    No Known Activations