© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47249
    Prev
    Next
    INDEX
    Explanations

    cutting board

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Cmd
    -0.81
     feasting
    -0.78
     sorties
    -0.75
     plazos
    -0.75
     adjustments
    -0.74
     DOR
    -0.71
     ordination
    -0.71
     산
    -0.71
    痛み
    -0.70
     firestore
    -0.69
    POSITIVE LOGITS
     cutting
    3.77
    Cutting
    3.20
     Cutting
    3.16
     chopping
    3.16
    cutting
    2.95
     board
    1.95
    CUT
    1.66
     CUT
    1.66
     cortar
    1.53
    Board
    1.51
    Activations Density 0.027%

    No Known Activations