© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90533
    Prev
    Next
    INDEX
    Explanations

    Parkinson, computed tomography, rotavirus, beta-blockers, antidepressants

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

    scientific and medical terminology related to biochemicals, diseases, and pharmaceutical compounds.

    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
    
    -1.12
    Rebs
    -1.09
     Obamacare
    -1.05
     Bestimm
    -1.00
    ほんとに
    -1.00
    もちろん
    -0.97
     lakini
    -0.96
     trainings
    -0.96
    色んな
    -0.93
     descobri
    -0.93
    POSITIVE LOGITS
     färg
    0.98
    硕士
    0.90
    驭
    0.89
    cipta
    0.89
     leopardo
    0.88
     or
    0.88
    新冠
    0.87
    岂
    0.87
    IDAE
    0.86
    edipus
    0.86
    Activations Density 1.232%

    No Known Activations