© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11479
    Prev
    Next
    INDEX
    Explanations

    location relative to ground

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

    output to screen or file

    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
    ༔
    0.42
    ሾ
    0.42
    एम
    0.40
    ழும்
    0.40
     każdej
    0.40
    ใ
    0.39
     минера
    0.39
     почита
    0.39
    ঔ
    0.39
     বিচারপতি
    0.38
    POSITIVE LOGITS
     ground
    1.25
    ground
    1.13
    地面
    1.11
     زمین
    1.02
    Ground
    1.00
     जमीन
    0.99
     Ground
    0.88
     GROUND
    0.87
     tanah
    0.83
    GROUND
    0.83
    Activations Density 0.440%

    No Known Activations