© 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. 198634
    Prev
    Next
    INDEX
    Explanations

    go to

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

    explaining language safety clarify hello

    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
     bipartite
    0.43
     tuple
    0.40
     INTO
    0.39
     these
    0.39
     markdown
    0.39
     curation
    0.39
    !*\
    0.38
     Figma
    0.38
    ’
    0.38
    tuple
    0.38
    POSITIVE LOGITS
     enfermos
    0.54
     برضو
    0.49
    とりあえず
    0.49
     enfermo
    0.49
     چاہی
    0.48
     namun
    0.48
     कित
    0.48
     jedoch
    0.47
    AllWindows
    0.47
     combatir
    0.47
    Activations Density 0.002%

    No Known Activations