© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 4043
    Prev
    Next
    INDEX
    Explanations

    fundamental nature of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     작품
    1.60
     φορ
    1.56
    菌
    1.53
     બાળકો
    1.42
     款
    1.41
     литератур
    1.39
     বিশ্ববিদ্যালয়ে
    1.39
    methyl
    1.39
     对象
    1.38
    窕
    1.38
    POSITIVE LOGITS
     bearish
    1.94
     bullish
    1.79
     Traders
    1.71
     Trading
    1.65
     trader
    1.63
     traders
    1.58
     trading
    1.49
    Trading
    1.48
     insiders
    1.40
     TI
    1.33
    Activations Density 0.323%

    No Known Activations