© 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. 192857
    Prev
    Next
    INDEX
    Explanations

    later, result, girl, boy, run

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

    new thresholds or changes

    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
     đóng
    0.47
     dần
    0.46
     wrong
    0.45
    r
    0.45
     defList
    0.44
     incidental
    0.44
     Đo
    0.43
     বস্ত
    0.43
     cảm
    0.43
    стема
    0.42
    POSITIVE LOGITS
    engar
    0.49
    нд
    0.43
    hofer
    0.42
    穷
    0.42
     toget
    0.42
    印度
    0.42
    窟
    0.42
    墘
    0.41
     concurred
    0.41
    ochet
    0.41
    Activations Density 0.001%

    No Known Activations