© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1307
    Prev
    Next
    INDEX
    Explanations

    Filipino language and Philippines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GCSE
    0.70
     운
    0.65
     ওয়া
    0.65
     হাতে
    0.64
     needn
    0.63
    ={'
    0.63
    Radians
    0.63
     পাল
    0.63
     পর
    0.63
    袤
    0.62
    POSITIVE LOGITS
     Philippine
    2.41
     Filipinos
    2.32
     Davao
    2.28
     Mindanao
    2.24
     Cebu
    2.24
     Filipino
    2.21
     Barangay
    2.13
     Quezon
    2.12
     Manila
    2.11
     Philippines
    2.05
    Activations Density 0.568%

    No Known Activations