© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 87176
    Prev
    Next
    INDEX
    Explanations

    Assisted Reproductive Technology

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

    The neuron detects the phrase "assisted reproductive technology" and related terms around assisted reproduction, suicide, or other assistance contexts.

    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_34/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
     waa
    -1.00
     pétrole
    -0.97
     クリニック
    -0.96
    '
    -0.96
    臯
    -0.92
    夘
    -0.91
    testimonial
    -0.91
     inmueble
    -0.91
    𝐡
    -0.91
     troisième
    -0.90
    POSITIVE LOGITS
     assist
    1.27
     блюдо
    1.07
    ances
    1.04
     Assist
    1.02
     Also
    1.02
     Required
    0.98
     Helping
    0.96
     crisp
    0.96
    anship
    0.95
     What
    0.94
    Activations Density 0.025%

    No Known Activations