© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8243
    Prev
    Next
    INDEX
    Explanations

    political dissidents and opposition

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

    censorship and suppression of dissent

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

    political dissidents

    np_max-act-logits · claude-4-5-sonnet
    Triggered by @skarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Microbial
    0.45
     microbial
    0.44
    끼
    0.42
     INFIN
    0.42
     लगेंगे
    0.42
    貔
    0.39
     ट्रॉफी
    0.39
    禮
    0.39
     वाइज
    0.38
     booster
    0.38
    POSITIVE LOGITS
     Amnesty
    1.27
     exiled
    1.13
     dissident
    1.09
     dissidents
    1.07
     exile
    1.03
     imprisoned
    0.97
     detained
    0.93
     activist
    0.93
     opposition
    0.91
     activists
    0.91
    Activations Density 0.203%

    No Known Activations