© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30685
    Prev
    Next
    INDEX
    Explanations

    Philippines, Filipinos, Manila

    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
    endan
    -0.77
    ISTER
    -0.77
    lich
    -0.76
     Courant
    -0.76
     adequately
    -0.74
     protest
    -0.72
     bawat
    -0.70
     sprach
    -0.69
    mmer
    -0.69
    entier
    -0.69
    POSITIVE LOGITS
     Philippines
    2.44
     Philippine
    2.34
     Filipino
    2.20
    Philippine
    2.09
    Philippines
    2.09
     Manila
    2.03
     Filipinos
    1.98
    Manila
    1.82
    philipp
    1.63
    Fili
    1.52
    Activations Density 0.039%

    No Known Activations