© 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. 10-GEMMASCOPE-RES-131K
    4. 130353
    Prev
    Next
    INDEX
    Explanations

    adenocarcinoma and adenylate

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

    medical and scientific terms containing "adeno" such as adenocarcinoma, adenovirus, or adenosine.

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

    The neuron is triggered by the “aden-” prefix (as in adenocarcinoma, adenovirus, adenosine, etc.).

    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
    尐
    -2.59
     Of
    -2.47
    C
    -2.27
    '
    -2.25
    把他
    -2.11
    ma
    -2.11
    鍮
    -2.05
    煳
    -2.05
    一键
    -2.05
    AILABILITY
    -2.05
    POSITIVE LOGITS
    ↵
    3.44
    тории
    2.25
    ен
    2.20
    ↑
    2.19
    ungkinkan
    2.19
     olvidar
    2.19
    ⟣
    2.13
    ꯵
    2.09
     Diese
    2.08
    瘣
    2.08
    Activations Density 0.020%

    No Known Activations