© 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. 22-GEMMASCOPE-RES-131K
    7. 33983
    Prev
    Next
    INDEX
    Explanations

    diseases developing or growing

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

    statistical or numerical data related to medical and scientific research.

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

    The main thing this neuron does is detect technical radiological or imaging terms (e.g. MRI, radiographic, spinal imaging) in medical text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     rimanere
    -0.96
     kembali
    -0.95
    әһ
    -0.89
     نگاه
    -0.85
     occhi
    -0.81
    失去
    -0.81
    posix
    -0.79
    Reduction
    -0.79
     '\
    -0.79
     redu
    -0.77
    POSITIVE LOGITS
     gradually
    1.80
     growing
    1.80
     now
    1.68
     already
    1.65
     developing
    1.62
    はまだ
    1.55
     beginning
    1.51
     Slowly
    1.50
     currently
    1.48
     rapidly
    1.45
    Activations Density 0.154%

    No Known Activations