© 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. 249877
    Prev
    Next
    INDEX
    Explanations

    comfort and ease

    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
     exercitation
    0.49
     termino
    0.49
     Thee
    0.48
     मासिक
    0.46
     компетен
    0.46
     modulo
    0.46
     kajian
    0.45
    ström
    0.45
     친
    0.45
    kei
    0.44
    POSITIVE LOGITS
    总
    0.50
    的总
    0.46
    総
    0.46
    ých
    0.46
    ನ್
    0.45
    onti
    0.45
    스크
    0.43
    getTotal
    0.43
     总
    0.43
    上次
    0.43
    Activations Density 0.000%

    No Known Activations