© 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. 14060
    Prev
    Next
    INDEX
    Explanations

    gynecological anatomical terms

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

    mentions of the uterus in medical and scientific texts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    Surprisingly
    -3.16
    趼
    -3.05
    ’
    -2.84
    𖡼
    -2.83
    that
    -2.67
     ostensibly
    -2.64
    e
    -2.64
     allow
    -2.59
     exquisitely
    -2.50
    Going
    -2.45
    POSITIVE LOGITS
     =
    3.31
    蓠
    3.02
     soooo
    2.89
     muitos
    2.81
     terrific
    2.80
     très
    2.75
     alguns
    2.73
     {
    2.73
     onze
    2.66
     sooo
    2.66
    Activations Density 0.043%

    No Known Activations