© 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. 75854
    Prev
    Next
    INDEX
    Explanations

    therapy and therapeutics

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

    The neuron identifies and activates on the word "therapeutic" and its variations like "therapeutically" or "therapeutics", particularly in medical and pharmaceutical contexts.

    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_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
     Wood
    -0.76
     Gunt
    -0.72
    endencia
    -0.72
    uage
    -0.72
    jny
    -0.68
     bulbs
    -0.66
    חים
    -0.66
    imageView
    -0.66
     buns
    -0.66
    Rite
    -0.65
    POSITIVE LOGITS
    tical
    1.55
    tics
    1.48
    tically
    1.42
    tic
    1.39
    ticals
    1.12
    tik
    0.97
    Fmt
    0.93
    Tick
    0.93
    tica
    0.86
    atic
    0.83
    Activations Density 0.057%

    No Known Activations