© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 98133
    Prev
    Next
    INDEX
    Explanations

    Malaysia

    np_acts-logits-general · gemini-2.5-flash-lite

    Malaysia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     სა
    0.52
     Hongkong
    0.47
     брига
    0.46
     WeChat
    0.43
    ࿐
    0.42
     ಸಾಕಷ್ಟು
    0.41
     PREVENTION
    0.41
    鈺
    0.41
     ም
    0.40
     learnt
    0.40
    POSITIVE LOGITS
    Malaysia
    0.90
     Malaysia
    0.89
     malaysia
    0.80
    马来
    0.77
     Malaysian
    0.76
     Kuala
    0.75
     Malays
    0.66
     मलेशिया
    0.64
     Selangor
    0.62
     Malay
    0.57
    Activations Density 0.044%

    No Known Activations