© 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. 221123
    Prev
    Next
    INDEX
    Explanations

    century, little, produced, resetting

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

    multiple optimal

    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
    一支
    0.44
     juncture
    0.44
     المل
    0.44
     précédemment
    0.44
     lineup
    0.44
    Diffusion
    0.44
     previous
    0.42
    種
    0.42
    previous
    0.42
     number
    0.41
    POSITIVE LOGITS
    д
    0.53
    duğu
    0.49
    ikia
    0.48
     mattered
    0.46
    जरी
    0.44
    ಾಗುತ್ತದೆ
    0.44
    תו
    0.43
    นา
    0.43
     Atkinson
    0.43
    държа
    0.43
    Activations Density 0.001%

    No Known Activations