© 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. 8181
    Prev
    Next
    INDEX
    Explanations

    insanity and absurdity

    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_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
    洊
    0.48
    eep
    0.45
    叹
    0.42
    慚
    0.42
     말미암
    0.40
    arakatuh
    0.40
     Vign
    0.40
     এইচডি
    0.40
     সহজাত
    0.39
    нету
    0.39
    POSITIVE LOGITS
     insane
    1.53
     crazy
    1.48
     insanity
    1.37
     craziness
    1.35
    crazy
    1.28
     madness
    1.27
     lunatic
    1.27
    瘋
    1.26
     Crazy
    1.23
    Crazy
    1.23
    Activations Density 0.290%

    No Known Activations