© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1119
    Prev
    Next
    INDEX
    Explanations

    parliament, election, constituency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
        
    0.80
       
    0.78
     അയ
    0.72
     delivery
    0.71
     knots
    0.67
    ುತ್ತ
    0.64
     constructor
    0.63
     দাঁ
    0.63
     sorted
    0.63
     w
    0.62
    POSITIVE LOGITS
     मतदारसं
    0.93
     मतदारसंघात
    0.85
    Parl
    0.81
    房价
    0.80
    racht
    0.74
    Parliament
    0.74
    fatt
    0.73
     парламент
    0.71
     Parl
    0.70
    ❝
    0.69
    Activations Density 0.125%

    No Known Activations