© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 151239
    Prev
    Next
    INDEX
    Explanations

    Rush Limbaugh, curse your blessings, Elizabeth Barrett

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

    internet slang and explanations

    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
    Not in Any Lists

    No Comments

    Negative Logits
    昕
    0.49
    ەوە
    0.47
    Ignore
    0.46
    ಕರ
    0.45
     unjustly
    0.45
     ఆట
    0.44
    ப்ர
    0.43
    ියේ
    0.43
     déprim
    0.43
    ⏸
    0.43
    POSITIVE LOGITS
    m
    0.53
    ਾਲ
    0.51
     DO
    0.48
     DON
    0.48
     Estonian
    0.46
     exemplos
    0.45
     projects
    0.44
     Liv
    0.44
     summarizes
    0.44
    িক
    0.44
    Activations Density 0.003%

    No Known Activations