© 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. 12662
    Prev
    Next
    INDEX
    Explanations

    AWS S3 buckets

    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
    UpdateChoice
    0.41
    ApiService
    0.40
     المركزي
    0.38
     turn
    0.37
    PathParam
    0.37
    newToken
    0.37
    finding
    0.36
    Gy
    0.36
    焙
    0.36
    RetResult
    0.36
    POSITIVE LOGITS
     bucket
    0.84
     buckets
    0.80
     Bucket
    0.79
    buckets
    0.74
    bucket
    0.72
    Bucket
    0.72
    桶
    0.65
     buck
    0.63
    BUCK
    0.60
    Buck
    0.57
    Activations Density 0.058%

    No Known Activations