© 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. 111679
    Prev
    Next
    INDEX
    Explanations

    Science, Medicine, Health, technical terms

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

    institutional names and professional titles like universities, laboratories, departments, and divisions.

    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
     already
    -1.70
     cũng
    -1.70
     also
    -1.65
     ebenfalls
    -1.60
     are
    -1.59
     similarly
    -1.51
     fabia
    -1.43
     they
    -1.41
     such
    -1.40
    亦
    -1.39
    POSITIVE LOGITS
     with
    1.56
    ۰۱
    1.54
     zelfs
    1.53
     ofrecen
    1.48
    Rys
    1.45
     proporcionan
    1.41
     comienzan
    1.39
     trattano
    1.39
     футболка
    1.36
    极为
    1.35
    Activations Density 0.130%

    No Known Activations