© 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. 8063
    Prev
    Next
    INDEX
    Explanations

    sleep patterns and disorders

    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
    Not in Any Lists

    No Comments

    Negative Logits
    лок
    0.43
    朝
    0.42
    ubjects
    0.40
    čního
    0.40
    то
    0.40
    ania
    0.40
    ậm
    0.40
    って
    0.39
    čních
    0.39
    Из
    0.39
    POSITIVE LOGITS
    💤
    0.52
     deprivation
    0.51
     deprived
    0.47
     profond
    0.46
     Makarna
    0.43
    😴
    0.43
     apnea
    0.43
    充足
    0.42
     tight
    0.41
     profundizar
    0.41
    Activations Density 0.061%

    No Known Activations