© 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. 20126
    Prev
    Next
    INDEX
    Explanations

    osteoarthritis OA

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

    medical and chemical terms with suffixes like "vynol," "nosus," "vitis," and "syno."

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron responds to the character sequence “no” (e.g. in tenosynovitis, synovial, peroneus, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Ꮵ
    -2.55
     pulsante
    -2.44
     They
    -2.39
     Primarily
    -2.36
    ?...
    -2.33
    烀
    -2.31
     tornare
    -2.30
    ໌
    -2.27
     Ironically
    -2.25
     diminutive
    -2.23
    POSITIVE LOGITS
    \
    2.91
    _
    2.84
     یک
    2.75
    僦
    2.41
    1
    2.41
    -
    2.31
     torsdag
    2.27
    AutoresizingMask
    2.25
    ↵↵
    2.22
     peut
    2.17
    Activations Density 0.098%

    No Known Activations