© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38534
    Prev
    Next
    INDEX
    Explanations

    endocrine disrupting chemicals

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

    chemical compounds and environmental pollutants, particularly focusing on toxic substances and their environmental impacts.

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

    The neuron detects mentions of chemical substances, especially names or classes of environmental pollutants (e.g. specific compounds, flame retardants, endocrine disruptors).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    一只
    -1.13
     was
    -1.09
    _
    -1.07
    preneurship
    -1.02
     psa
    -1.02
    STUD
    -1.00
     sentimento
    -1.00
     marseille
    -1.00
     fiscales
    -0.99
     agré
    -0.98
    POSITIVE LOGITS
    lectoral
    1.20
    ógy
    1.17
     our
    1.12
     нашим
    1.10
    Litteratur
    1.09
     PUSTAKA
    1.08
     sàng
    1.07
    jadikan
    1.07
     navn
    1.05
     siglas
    1.04
    Activations Density 0.191%

    No Known Activations