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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109842
    Prev
    Next
    INDEX
    Explanations

    drug and brand names

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

    brand names of pharmaceutical products or medications.

    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
     phonics
    -0.82
    Horm
    -0.81
    呜
    -0.79
    kauf
    -0.77
     CHEM
    -0.77
    baren
    -0.75
    нија
    -0.75
    無論
    -0.74
    ātu
    -0.74
     ミニ
    -0.72
    POSITIVE LOGITS
    ®
    1.90
     Plus
    1.48
    ™
    1.45
    Plus
    1.33
     ®
    1.33
    ®,
    1.28
    ®.
    1.22
     forte
    1.18
    plus
    1.15
     Forte
    1.11
    Activations Density 0.066%

    No Known Activations