© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12195
    Prev
    Next
    INDEX
    Explanations

    reproductive health and ability

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

    The neuron identifies scientific terms related to reproduction and reproductive biology.

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

    The neuron consistently activates on the term “reproductive,” flagging occurrences of that word in various biological or medical contexts.

    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
    BIÉN
    -2.20
     '
    -2.11
    ড
    -2.05
    derdag
    -2.03
    ."
    -1.98
    ࿙
    -1.96
     "
    -1.95
    请问
    -1.95
     mantan
    -1.92
    紝
    -1.91
    POSITIVE LOGITS
    䊳
    2.06
    𝓚
    2.03
     Reproductive
    2.03
     your
    2.02
    鸕
    1.98
     einschließlich
    1.97
     manteniendo
    1.97
    2
    1.96
    Ꮟ
    1.96
    ꯵
    1.93
    Activations Density 0.011%

    No Known Activations