© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12841
    Prev
    Next
    INDEX
    Explanations

    rBST/rBGH, protection, company

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

    breast milk jobs

    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_16k_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
     عراق
    0.33
    బ్‌
    0.32
    اند
    0.31
    强者
    0.31
    укра
    0.30
    ड़ियां
    0.30
     Liet
    0.29
    ϭ
    0.29
    oters
    0.29
     эшлә
    0.29
    POSITIVE LOGITS
     ಮುಂದೆ
    0.32
     B
    0.30
     CH
    0.29
     তৎকালীন
    0.29
     P
    0.29
     Lorsque
    0.28
     পরবর্ত
    0.27
    িত্যক্ত
    0.27
     বিপ
    0.26
     बीएड
    0.26
    Activations Density 0.321%

    No Known Activations