© 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. 10-GEMMASCOPE-RES-131K
    7. 15637
    Prev
    Next
    INDEX
    Explanations

    killings and murders

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    给我们
    -1.52
     luxem
    -1.40
     piac
    -1.39
    赑
    -1.36
     CONTR
    -1.35
     friv
    -1.35
    strerror
    -1.34
     ered
    -1.34
     lagar
    -1.33
     comport
    -1.32
    POSITIVE LOGITS
    ↵
    1.95
     by
    1.80
     It
    1.38
     falschen
    1.34
    意
    1.32
     ليس
    1.31
    vège
    1.29
     There
    1.27
    щность
    1.27
     gän
    1.21
    Activations Density 0.085%

    No Known Activations