© 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. 10-GEMMASCOPE-RES-131K
    7. 102992
    Prev
    Next
    INDEX
    Explanations

    elderly patients and health

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

    The neuron detects references to elderly people, including words like "elderly" and "elders".

    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
     récolte
    -2.20
    indelijk
    -2.17
    rschein
    -2.14
     grève
    -2.08
     我们
    -2.06
     conceivably
    -2.06
    ༴
    -2.05
    蕷
    -2.03
       
    -2.00
    ᚔ
    -2.00
    POSITIVE LOGITS
    鹮
    3.22
    ſſel
    2.91
    they
    2.83
     powinien
    2.70
    鸶
    2.66
    there
    2.63
    we
    2.58
     tohto
    2.55
    这种
    2.53
     этом
    2.48
    Activations Density 0.003%

    No Known Activations