© 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-65K
    7. 47366
    Prev
    Next
    INDEX
    Explanations

    tracing outlines or paths

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ponctué
    0.46
     triun
    0.43
    ITES
    0.42
     eficacia
    0.41
    ဏ်
    0.40
     intensidad
    0.39
     scorecard
    0.39
    vii
    0.39
    삑
    0.39
     integrantes
    0.38
    POSITIVE LOGITS
     trace
    1.73
    Trace
    1.58
     Trace
    1.55
    trace
    1.55
     traced
    1.54
     tracing
    1.48
    Tracing
    1.34
     traces
    1.26
     traceable
    1.26
    tracing
    1.24
    Activations Density 0.018%

    No Known Activations