© 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. 79481
    Prev
    Next
    INDEX
    Explanations

    global agreement on carbon emissions

    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
    きたいと思います
    -0.85
    腟
    -0.77
    categoria
    -0.77
     culturales
    -0.76
    PDM
    -0.76
    TTY
    -0.75
    siella
    -0.74
    ismic
    -0.74
    gige
    -0.73
     benessere
    -0.73
    POSITIVE LOGITS
     carbon
    1.88
     Carbon
    1.51
    carbon
    1.41
     ETS
    1.33
     CARBON
    1.26
    Carbon
    1.25
     price
    1.25
     pricing
    1.19
     cap
    1.09
    碳
    1.08
    Activations Density 0.013%

    No Known Activations