© 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. 34-GEMMASCOPE-RES-131K
    7. 78883
    Prev
    Next
    INDEX
    Explanations

    dosage frequency and units

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

    medication dosing instructions, particularly quantities and frequency of administration in medical 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
    ண்டு
    -0.85
     dzięki
    -0.82
    -0.80
     hampir
    -0.78
     സ്
    -0.78
     indexed
    -0.77
    ensas
    -0.76
     gehören
    -0.74
     از
    -0.74
    setItem
    -0.74
    POSITIVE LOGITS
     daily
    2.06
     twice
    1.84
    daily
    1.63
    twice
    1.48
     morning
    1.39
    DAILY
    1.35
     day
    1.34
    Daily
    1.33
     Daily
    1.30
     thrice
    1.30
    Activations Density 0.109%

    No Known Activations