© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105999
    Prev
    Next
    INDEX
    Explanations

    adjective + descriptive word

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Ǔ
    -1.36
     such
    -1.33
     alcuni
    -1.27
     Nieuws
    -1.25
     alcune
    -1.22
    ₃
    -1.20
    які
    -1.16
     pisze
    -1.14
    ₆
    -1.14
     certaines
    -1.13
    POSITIVE LOGITS
     only
    1.51
    因为它
    1.25
    </b>
    1.23
    同一个
    1.23
     يعرف
    1.15
    鱟
    1.09
     épreuve
    1.05
    ماذا
    1.05
    なんだろう
    1.05
     also
    1.03
    Activations Density 0.140%

    No Known Activations