© 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. 104118
    Prev
    Next
    INDEX
    Explanations

    semen parameters

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

    references to semen or biological fluids in scientific/medical texts.

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

    The neuron specializes in detecting mentions of male reproductive material (sperm cells or semen) in the 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
    ꜆
    -2.88
    ON
    -2.61
    鰨
    -2.59
    壜
    -2.42
    AN
    -2.41
    剩下
    -2.39
    ⢮
    -2.36
    臈
    -2.36
    我真的
    -2.28
    N
    -2.28
    POSITIVE LOGITS
          
    3.02
     gewünschten
    2.42
     برای
    2.39
     یک
    2.39
    это
    2.38
    豔
    2.34
             
    2.30
     для
    2.25
    严重的
    2.25
    觏
    2.23
    Activations Density 0.023%

    No Known Activations