© 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-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 12386
    Prev
    Next
    INDEX
    Explanations

    fake, fictional, pretend, simulate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     мел
    0.45
    meros
    0.38
     hidden
    0.37
     Dw
    0.37
     смесь
    0.37
     Tron
    0.36
     ó
    0.36
     TAM
    0.36
     embedding
    0.35
     méthodique
    0.35
    POSITIVE LOGITS
    假的
    0.68
    Fake
    0.66
     fake
    0.66
     faux
    0.65
     Fake
    0.62
    假
    0.62
     simulate
    0.59
    fake
    0.59
    pseudo
    0.59
     pretend
    0.58
    Activations Density 0.170%

    No Known Activations