© 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. 53-GEMMASCOPE-2-RES-65K
    7. 17720
    Prev
    Next
    INDEX
    Explanations

    `using System.Threading.Tasks`

    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_53_width_65k_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
    ത്തിലേ
    0.43
     ঘোষণার
    0.40
     শর
    0.40
    -[#
    0.40
     ナイロン
    0.40
     Substances
    0.39
     EPS
    0.39
    ".[
    0.38
    東西
    0.38
     absol
    0.37
    POSITIVE LOGITS
     Robust
    0.54
    Robust
    0.51
     robuste
    0.50
     robust
    0.50
    robust
    0.48
    PRET
    0.44
    pret
    0.43
     toggle
    0.43
     prét
    0.42
     बिफोर
    0.42
    Activations Density 0.000%

    No Known Activations