© 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. 16-GEMMASCOPE-2-RES-262K
    7. 4879
    Prev
    Next
    INDEX
    Explanations

    cleaning, feeding, or disposing

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ki
    0.43
     runde
    0.42
     anderem
    0.42
     verdens
    0.41
    "){
    0.40
     zehn
    0.39
     kontinu
    0.39
     manuf
    0.39
     whatnot
    0.39
     jaune
    0.38
    POSITIVE LOGITS
    بود
    0.42
     Mood
    0.40
    })$
    0.39
     ঘা
    0.38
    보
    0.38
    ాలు
    0.37
    તી
    0.36
     Forbes
    0.36
    })\
    0.36
    의
    0.36
    Activations Density 0.065%

    No Known Activations