© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14606
    Prev
    Next
    INDEX
    Explanations

    ur combined with medical or web terms

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

    words starting with "ur" particularly related to computing/web terminology and 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
    觧
    -3.14
     моя
    -2.88
    饪
    -2.84
    ⑊
    -2.72
     bilhões
    -2.66
    riculares
    -2.64
    <bos>
    -2.64
    quelize
    -2.64
    usitis
    -2.59
    ⬯
    -2.59
    POSITIVE LOGITS
     Because
    2.44
    "
    2.34
     lure
    2.27
     Until
    2.22
    *
    2.19
     messing
    2.16
    她就
    2.14
    As
    2.14
    配音
    2.14
     –
    2.13
    Activations Density 0.004%

    No Known Activations