© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10392
    Prev
    Next
    INDEX
    Explanations

    location name following `in`

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

    regions and provinces

    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_40_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
    滇
    0.54
     Pensacola
    0.53
    渝
    0.52
    瀘
    0.49
     Dubrovnik
    0.49
    緬
    0.48
     Border
    0.47
     কক্স
    0.46
     मणिपुर
    0.45
    沖縄
    0.44
    POSITIVE LOGITS
    爌
    0.61
     திருச்சி
    0.55
     Midland
    0.52
    胙
    0.51
    彰
    0.48
    颍
    0.47
     বগু
    0.45
     Waco
    0.43
     Midlands
    0.43
    邙
    0.41
    Activations Density 0.787%

    No Known Activations