© 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. 8720
    Prev
    Next
    INDEX
    Explanations

    medical and health conditions

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

    technical terms in specialized fields like technology, medicine, and science.

    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
     is
    -1.27
    tuce
    -1.24
    겟
    -1.20
    tops
    -1.18
    asibility
    -1.16
    __',
    -1.15
    preneurs
    -1.14
    PMID
    -1.11
    şekkür
    -1.11
    align
    -1.09
    POSITIVE LOGITS
     they
    1.63
     for
    1.53
     their
    1.31
    你这个
    1.23
     ymm
    1.19
    ჱ
    1.18
    にします
    1.17
     women
    1.16
     with
    1.14
     для
    1.13
    Activations Density 0.455%

    No Known Activations