© 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. 81574
    Prev
    Next
    INDEX
    Explanations

    Finally

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

    try to predict

    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
    3
    0.52
    𝟎
    0.50
    SPI
    0.50
    attempt
    0.48
    ３
    0.47
    ؤ
    0.47
     je
    0.46
     पला
    0.46
    6
    0.45
    دن
    0.45
    POSITIVE LOGITS
     inutile
    0.49
    cuterie
    0.48
    readystatechange
    0.47
     בדי
    0.47
     മറ്റൊരു
    0.47
     tern
    0.46
     erneut
    0.46
    칙
    0.46
    리학
    0.45
    탉
    0.45
    Activations Density 0.001%

    No Known Activations