© 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. 44418
    Prev
    Next
    INDEX
    Explanations

    administration of substances

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

    words related to drug or substance administration in scientific/medical contexts.

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

    The neuron is selectively detecting numerical measurement expressions—especially dosage amounts, administration counts, and similar numeric values in scientific 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_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
    and
    -2.14
    w
    -1.73
     و
    -1.71
     другое
    -1.62
     fanta
    -1.61
    witter
    -1.53
     burberry
    -1.49
     grotes
    -1.49
     brillant
    -1.48
     minne
    -1.48
    POSITIVE LOGITS
     to
    2.09
     any
    1.86
     Combining
    1.84
    ܜ
    1.81
     in
    1.77
     large
    1.68
     severely
    1.66
     time
    1.66
     used
    1.66
    勦
    1.65
    Activations Density 0.248%

    No Known Activations