© 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-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 4235
    Prev
    Next
    INDEX
    Explanations

    Australian domains and countries

    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
     Mérida
    0.80
     Donetsk
    0.79
     Vito
    0.76
     Yolanda
    0.75
    肝
    0.73
     Ghulam
    0.72
    蟹
    0.71
    djang
    0.70
    滕
    0.70
     пище
    0.70
    POSITIVE LOGITS
     Australian
    2.61
     Australia
    2.52
     AU
    2.49
     austral
    2.47
    Australian
    2.45
     Aussie
    2.40
    Australia
    2.39
    AU
    2.34
     AUSTRAL
    2.34
     Австра
    2.32
    Activations Density 0.018%

    No Known Activations