© 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. 67229
    Prev
    Next
    INDEX
    Explanations

    unsaturated compounds and fats

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

    The neuron identifies words containing the root "unsaturated" particularly in scientific and chemical contexts.

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

    The neuron is triggered by occurrences of the letter sequence “uns,” e.g. in words like “unsaturated” or “unsubscribe.”

    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
    ться
    -3.20
    不会
    -3.09
    很少
    -3.06
    不是
    -2.84
    an
    -2.78
    就是
    -2.70
     如果
    -2.70
    on
    -2.67
    P
    -2.63
    al
    -2.55
    POSITIVE LOGITS
    ᯾
    2.52
    酝
    2.25
    姈
    2.17
     チラ
    2.14
    ’
    2.13
     blah
    2.11
    ཪ
    2.09
     techniczne
    2.09
     camiset
    2.06
    “
    2.05
    Activations Density 0.002%

    No Known Activations