© 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. 34-GEMMASCOPE-RES-131K
    7. 76260
    Prev
    Next
    INDEX
    Explanations

    Adrian names and medical terms

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

    names starting with "Adri" or "Adrian" like Adrian, Adriana, Adrienne, and Adriamycin.

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

    The neuron responds strongly to words beginning with the letter sequence “Adri,” such as drug names (Adriamycin) or proper names (Adrian, Adrienne).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Alemania
    -0.75
    Additional
    -0.75
     Behörden
    -0.74
    ńskiej
    -0.72
     обо
    -0.72
    ranos
    -0.72
     compelled
    -0.71
     gesloten
    -0.70
     Additional
    -0.70
     central
    -0.68
    POSITIVE LOGITS
    ContextMenu
    0.86
    ssens
    0.84
    eps
    0.84
    Curves
    0.84
    amycin
    0.81
    ople
    0.77
    limits
    0.75
    Zend
    0.75
     ရ
    0.75
     психо
    0.74
    Activations Density 0.026%

    No Known Activations