© 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. 10-GEMMASCOPE-RES-131K
    4. 10139
    Prev
    Next
    INDEX
    Explanations

    pharmacy and related roles

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

    references to pharmacies, pharmacy settings, or 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_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
    ?"
    -3.41
     was
    -3.30
    泐
    -3.22
     furthermore
    -2.94
     are
    -2.75
    佧
    -2.67
     女子
    -2.59
     said
    -2.56
    光是
    -2.41
     kimdir
    -2.36
    POSITIVE LOGITS
    ↵↵
    3.84
     Erhöhung
    2.59
    Ꮸ
    2.39
    .
    2.36
    anyahu
    2.36
    ᠁
    2.27
     знали
    2.27
    龊
    2.16
    a
    2.14
    羕
    2.13
    Activations Density 0.004%

    No Known Activations