© 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. 73308
    Prev
    Next
    INDEX
    Explanations

    male reproductive hormones

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

    topics related to male biology, sexuality, or gender roles.

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

    The neuron fires on numeric expressions—especially decimal‐style statistics, measurements, and other figures.

    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
     herself
    -1.55
    为你
    -1.32
    athed
    -1.23
    textAppearance
    -1.23
     douleur
    -1.22
    Avez
    -1.21
    both
    -1.20
     souffrance
    -1.18
     both
    -1.14
     disparition
    -1.14
    POSITIVE LOGITS
     himself
    2.70
    f
    1.38
     نفسه
    1.36
     mismo
    1.28
     zijn
    1.24
    himself
    1.23
    FullScreen
    1.16
    < 
    1.16
     Jr
    1.15
    is
    1.13
    Activations Density 0.337%

    No Known Activations