© 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. 111606
    Prev
    Next
    INDEX
    Explanations

    99mTc imaging

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

    Chemical or technical notation with "m" after numbers, particularly in scientific contexts like radiopharmaceuticals (99mTc).

    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
    wanzig
    -1.93
     armé
    -1.55
     However
    -1.53
     triko
    -1.45
     桌面
    -1.44
     doba
    -1.42
    </h2>
    -1.41
     suprême
    -1.41
     土豆
    -1.40
     okru
    -1.38
    POSITIVE LOGITS
     größe
    1.54
    先是
    1.48
    seems
    1.48
    tells
    1.46
    itizing
    1.46
     antaranya
    1.45
    aned
    1.44
    preparing
    1.43
    NOTAS
    1.43
    really
    1.42
    Activations Density 0.000%

    No Known Activations