© 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. 57061
    Prev
    Next
    INDEX
    Explanations

    herbal medicine

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

    Embedding

    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
    赋值
    0.48
    ંધ
    0.46
    ЛИ
    0.46
    Jazz
    0.46
    🎟
    0.46
    কারি
    0.45
     collegiate
    0.45
     fade
    0.44
    тивность
    0.44
     હજાર
    0.44
    POSITIVE LOGITS
     Guill
    0.52
     Nied
    0.50
     ис
    0.49
     Eigent
    0.49
     Chinn
    0.49
     chicas
    0.47
     阿
    0.47
     Ewing
    0.47
     Еў
    0.47
     Erinner
    0.47
    Activations Density 0.000%

    No Known Activations