© 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. 42923
    Prev
    Next
    INDEX
    Explanations

    immortalized biological cells

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

    words with the suffix "-ized" or "-ization", particularly related to scientific or medical 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_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
     we
    -3.41
    t
    -2.50
    檮
    -2.48
     Of
    -2.42
    人的
    -2.41
    ra
    -2.39
     maxim
    -2.39
    那种
    -2.38
     работал
    -2.33
     enmar
    -2.33
    POSITIVE LOGITS
     故事
    2.73
    韞
    2.52
    ㄨ
    2.44
    葙
    2.44
    神
    2.44
    神経
    2.42
     हालांकि
    2.42
     邸
    2.41
    Специ
    2.36
     韓
    2.34
    Activations Density 0.131%

    No Known Activations