© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3578
    Prev
    Next
    INDEX
    Explanations

    scientific and biological research

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

    scientific research reporting in formal articles, particularly focusing on biology, genetics, and environmental studies.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered 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
    Negative Logits
     utilizan
    -1.11
     również
    -1.10
     utilizado
    -1.05
     utilizar
    -1.04
     kapturem
    -1.03
     hysterical
    -1.03
    大量的
    -1.02
     dán
    -1.01
    鍼
    -1.00
     Utilize
    -0.99
    POSITIVE LOGITS
     keineswegs
    1.09
    iding
    1.08
     nötig
    1.06
     היתה
    1.06
     flick
    1.05
     isn
    1.04
    Earth
    1.02
    arxiv
    1.01
    ⊓
    1.00
    couldn
    0.99
    Activations Density 0.130%

    No Known Activations