© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32766
    Prev
    Next
    INDEX
    Explanations

    Eastern origin and culture

    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
    Not in Any Lists

    No Comments

    Negative Logits
    rodní
    -0.73
    zar
    -0.71
     pik
    -0.66
     Dyke
    -0.65
     polymer
    -0.65
    violation
    -0.64
     مج
    -0.64
     elimination
    -0.64
     याद
    -0.63
    𝒌
    -0.63
    POSITIVE LOGITS
     translations
    0.92
     Oriental
    0.88
    судар
    0.84
     colo
    0.82
     oriental
    0.81
    ତ
    0.79
     asiatique
    0.79
     religions
    0.79
     Religions
    0.78
     Yoga
    0.77
    Activations Density 0.025%

    No Known Activations