© 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. 15840
    Prev
    Next
    INDEX
    Explanations

    drug and rehabilitation treatments

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

    completing 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
    рін
    0.46
    
    0.42
    \\\
    0.40
    ANTES
    0.40
    等的
    0.40
     olmak
    0.39
    ıkları
    0.39
    entuk
    0.39
    ÜR
    0.39
     আৰ
    0.39
    POSITIVE LOGITS
     pharm
    0.47
     sailboat
    0.41
     interessant
    0.40
     pharmacy
    0.39
    藥
    0.39
     phage
    0.39
    药品
    0.38
     کشت
    0.38
     intéressante
    0.38
     jetty
    0.38
    Activations Density 0.006%

    No Known Activations