© 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. 109683
    Prev
    Next
    INDEX
    Explanations

    bio-TNF blockers

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

    names of pharmaceutical drugs and medical treatments, particularly immunosuppressants and anti-inflammatory 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
     géné
    -0.85
    utra
    -0.84
     Worm
    -0.78
    杓
    -0.73
    ṇ
    -0.71
     hermanos
    -0.70
     grado
    -0.69
     nuestro
    -0.69
    лаго
    -0.68
    ယ်
    -0.68
    POSITIVE LOGITS
     biolog
    1.17
     biologic
    1.08
     TNF
    1.08
    imab
    0.93
    TNF
    0.93
     Rheumat
    0.90
    renza
    0.87
     Rit
    0.87
    生物
    0.86
     meth
    0.86
    Activations Density 0.097%

    No Known Activations