© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 28503
    Prev
    Next
    INDEX
    Explanations

    Sichuan province

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_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
     Tauri
    0.47
    Cau
    0.41
    Chennai
    0.41
    Tamil
    0.40
    Outcome
    0.40
     Laure
    0.39
    椥
    0.39
    莜
    0.38
     Cauchy
    0.38
     Kari
    0.37
    POSITIVE LOGITS
     Sichuan
    0.57
    泸
    0.55
    四川
    0.54
     Chengdu
    0.49
    阆
    0.46
     부여
    0.43
    黔
    0.43
    成都
    0.42
     Shropshire
    0.42
     سوری
    0.42
    Activations Density 0.003%

    No Known Activations