© 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-262K
    7. 165993
    Prev
    Next
    INDEX
    Explanations

    drug names and dosages

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

    medical conditions and treatments

    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
     weihn
    0.62
     Origami
    0.58
     Cards
    0.57
    🎄
    0.56
     origami
    0.56
     জন্মদিন
    0.55
     popup
    0.55
     cards
    0.54
     های
    0.54
     শিপ
    0.54
    POSITIVE LOGITS
    itochond
    0.59
    病情
    0.52
     clinical
    0.50
     metabolism
    0.49
     Symptoms
    0.49
     intolerance
    0.49
     catechol
    0.48
    deoxy
    0.48
    芪
    0.48
     clinically
    0.48
    Activations Density 0.004%

    No Known Activations