© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 60658
    Prev
    Next
    INDEX
    Explanations

    menopausal women or estrogen

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

    words related to comparative forms like "menos" (less), "menor" (smaller), or "menopausal" in different languages.

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

    The neuron is triggered by the subword “meno” (e.g. in “menopausal”), i.e. terms related to menopause.

    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
    derdag
    -2.88
    桄
    -2.80
    geſ
    -2.77
     nových
    -2.55
    锨
    -2.48
    akteur
    -2.39
    nobyl
    -2.38
     farbe
    -2.36
     úspě
    -2.36
     formidable
    -2.34
    POSITIVE LOGITS
    ет
    2.97
    -
    2.70
    It
    2.70
    橚
    2.64
    芣
    2.48
     -
    2.47
    <em>
    2.44
    蔟
    2.38
    蚡
    2.36
    神情
    2.33
    Activations Density 0.002%

    No Known Activations