© 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. 14192
    Prev
    Next
    INDEX
    Explanations

    supra + medicine/anatomy/science

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

    anatomical terms with the prefix "supra-".

    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
    {
    -2.34
     The
    -2.19
     především
    -1.93
     ‘
    -1.89
    —“
    -1.88
    有助
    -1.81
    ”.
    -1.78
    ’:
    -1.78
     bahwa
    -1.76
    ":
    -1.76
    POSITIVE LOGITS
     tabak
    2.73
     abiye
    2.58
     banyo
    2.48
     bardak
    2.45
     anadolu
    2.41
     diki
    2.38
     parfü
    2.36
     yüzük
    2.28
     dekoratif
    2.25
     katk
    2.25
    Activations Density 0.001%

    No Known Activations