© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6478
    Prev
    Next
    INDEX
    Explanations

    code examples and calculations

    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_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ুরের
    0.44
    leyeceğiz
    0.43
    പാടി
    0.41
    barui
    0.41
    rdquo
    0.40
     entrambe
    0.38
    ០
    0.38
    árez
    0.38
    örn
    0.38
    亅
    0.37
    POSITIVE LOGITS
     but
    0.42
    と思いますが
    0.40
     or
    0.40
    ますが
    0.36
     lead
    0.36
    しますが
    0.35
     instead
    0.35
     j
    0.34
     infil
    0.34
     rink
    0.34
    Activations Density 0.249%

    No Known Activations