© 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-65K
    7. 2199
    Prev
    Next
    INDEX
    Explanations

    Philippine and Filipino culture

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tucker
    0.71
    袤
    0.71
    Wald
    0.71
    闂
    0.70
     স্
    0.70
     ইরান
    0.69
     Zeich
    0.69
     सर्दियों
    0.69
     それ
    0.68
     algorith
    0.67
    POSITIVE LOGITS
     Philippine
    2.99
     Filipino
    2.89
     Filipinos
    2.89
     Philippines
    2.86
    Philippines
    2.71
     Manila
    2.59
     Cebu
    2.49
    ₱
    2.43
    菲律
    2.41
     Mindanao
    2.36
    Activations Density 0.041%

    No Known Activations