© 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. 218838
    Prev
    Next
    INDEX
    Explanations

    societal criticism politics communism ideologies

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

    people and generations

    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
    𝗁
    0.48
     tooltip
    0.46
    rupole
    0.46
     potwier
    0.46
     datap
    0.46
    codewords
    0.46
     कानूनी
    0.46
     ಈಗಾಗಲೇ
    0.46
    rollerskates
    0.46
    🔍
    0.46
    POSITIVE LOGITS
     Politicians
    0.64
     politicians
    0.61
     Millennials
    0.56
     selfishness
    0.54
     políticos
    0.53
     philosophers
    0.53
     laziness
    0.53
     materialism
    0.52
     arrogant
    0.51
     Communism
    0.51
    Activations Density 0.139%

    No Known Activations