© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 195284
    Prev
    Next
    INDEX
    Explanations

    pharma, biotech, and life sciences

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

    pharmaceuticals and related industries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     экстре
    0.53
    赈
    0.48
    铁路
    0.46
    ເຄື່ອງ
    0.46
    ellery
    0.46
    簸
    0.45
    แมนเชสเตอร์ซิตี
    0.45
    แหน
    0.44
    镤
    0.44
    帜
    0.44
    POSITIVE LOGITS
     pharma
    1.41
     pharmaceutical
    1.33
    Pharmaceutical
    1.27
     Pharma
    1.26
     pharmaceut
    1.22
     Pharmaceutical
    1.20
     pharmaceuticals
    1.17
    pharm
    1.14
     pharm
    1.11
     pharmac
    1.09
    Activations Density 0.106%

    No Known Activations