© 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. 1944
    Prev
    Next
    INDEX
    Explanations

    foreign words and medical terms

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

    phrases containing "of" followed by words related to medical, scientific, or institutional terms.

    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
    などを
    -1.06
     décoration
    -1.05
    

    -1.02
    ob
    -0.98
    made
    -0.96
     '
    -0.96
    抿
    -0.96
    そして
    -0.94
     antik
    -0.94
     offens
    -0.93
    POSITIVE LOGITS
    hæng
    1.23
    찔
    1.15
     leyendo
    1.12
     znam
    1.07
     Persönlichkeit
    1.05
    ˮ
    1.05
     étrangère
    1.04
     tkan
    1.02
     aluminio
    1.02
     nadru
    1.02
    Activations Density 0.213%

    No Known Activations