© 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. 11900
    Prev
    Next
    INDEX
    Explanations

    carrying items by hand

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

    grip and holding

    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
    ズム
    0.39
    MEA
    0.37
    edra
    0.37
    媜
    0.37
     divisors
    0.36
    ⬝
    0.35
     ডিপ
    0.34
    മ്പ്
    0.33
    ilaire
    0.33
    拉
    0.33
    POSITIVE LOGITS
    手中
    1.67
    手里
    1.64
    手に
    1.56
     руках
    1.45
     হাতে
    1.38
    手上
    1.37
     hand
    1.36
     handheld
    1.33
     handen
    1.32
    手中的
    1.32
    Activations Density 0.275%

    No Known Activations