© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81650
    Prev
    Next
    INDEX
    Explanations

    projection, pharma, sequential, pain, October

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

    The neuron fires on specialized technical terms and acronyms from scientific imaging papers (e.g. statistical reconstruction, PET/CT, OS-EM, SPECT, Monte Carlo), so it’s detecting highly domain-specific biomedical imaging jargon.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     products
    -0.97
    产品
    -0.84
     product
    -0.82
     Products
    -0.81
    TUN
    -0.74
     potential
    -0.73
     ben
    -0.71
    劈
    -0.71
    <0xA7>
    -0.69
     jo
    -0.69
    POSITIVE LOGITS
     Tuy
    1.16
    Tuy
    1.02
     Projections
    0.96
     Radon
    0.92
    Sin
    0.90
     LOR
    0.86
     rayons
    0.85
     radon
    0.84
    sint
    0.84
     molybdenum
    0.84
    Activations Density 0.062%

    No Known Activations