© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 2142
    Prev
    Next
    INDEX
    Explanations

    employment and job impacts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    扈
    1.15
    ler
    1.12
    ીર
    1.10
    ing
    1.07
    urada
    1.07
    szág
    1.03
    erina
    1.00
    ar
    0.97
    y
    0.95
     prist
    0.94
    POSITIVE LOGITS
    certificado
    2.25
     BENEFITS
    2.25
    oflav
    2.24
     calificación
    2.12
     felices
    2.12
     certificados
    2.11
     entitles
    2.10
     SUMMARY
    2.09
     humiliation
    2.08
     beneficios
    2.07
    Activations Density 0.224%

    No Known Activations