© 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-16K
    7. 11503
    Prev
    Next
    INDEX
    Explanations

    third side

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

    credential dumping from memory

    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_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     반지름
    0.46
     উপনিবেশ
    0.43
     যৌগ
    0.41
    圆形
    0.41
     orang
    0.41
    ജ്യ
    0.41
     cub
    0.41
     공간
    0.41
     YMCA
    0.40
    枤
    0.40
    POSITIVE LOGITS
    DF
    0.50
     ae
    0.45
    DCs
    0.45
    IEEE
    0.43
    protect
    0.43
     exhibited
    0.42
    authentication
    0.41
    Nep
    0.41
     milites
    0.41
    Power
    0.41
    Activations Density 0.034%

    No Known Activations