© 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. 246689
    Prev
    Next
    INDEX
    Explanations

    waste, spokesman, renovation, fashion

    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
    Negative Logits
     மேலே
    0.53
     وتح
    0.50
     วัด
    0.47
     sweetest
    0.46
     בח
    0.45
     则
    0.45
     වීම
    0.45
    扡
    0.45
     fervent
    0.44
     Untersuchung
    0.44
    POSITIVE LOGITS
    ●
    0.47
     congr
    0.45
    ᱤ
    0.44
    novation
    0.43
    product
    0.43
    pand
    0.43
     আর্টি
    0.43
    比亚
    0.43
     confer
    0.43
    不是
    0.42
    Activations Density 0.000%

    No Known Activations