© 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. 147556
    Prev
    Next
    INDEX
    Explanations

    on, info, shoe, difference

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

    highly regulated, complex

    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
    ové
    0.47
    interpretation
    0.47
    translational
    0.46
    un
    0.45
    拯
    0.45
     Zelensky
    0.44
    řed
    0.44
     ና
    0.44
    asidd
    0.43
    header
    0.43
    POSITIVE LOGITS
    ниях
    0.50
     kanak
    0.48
    PRESSED
    0.47
     exerc
    0.46
    τητα
    0.46
     luar
    0.45
     accrue
    0.45
    :
    0.45
     arme
    0.44
     lokalen
    0.44
    Activations Density 0.001%

    No Known Activations