© 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. 10-GEMMASCOPE-RES-131K
    7. 71956
    Prev
    Next
    INDEX
    Explanations

    anesthetic, inhibitor, drug, or peptide names

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

    pharmaceutical and chemical compounds in medical/scientific text.

    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
     they
    -1.29
     from
    -1.26
    ).
    -1.24
     but
    -1.20
     such
    -1.16
     on
    -1.04
    ').
    -1.02
     unholy
    -1.01
    Тарихы
    -1.01
     pubblicato
    -1.01
    POSITIVE LOGITS
    𝗾
    1.16
    ዕ
    1.14
    体现
    1.12
    zyści
    1.12
    punkten
    1.10
    omorphisms
    1.09
     dissent
    1.09
    existence
    1.08
    ffl
    1.08
    ÜR
    1.05
    Activations Density 0.198%

    No Known Activations