© 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. 13-GEMMASCOPE-2-RES-16K
    7. 13258
    Prev
    Next
    INDEX
    Explanations

    top with or on top of

    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_13_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
     मैनु
    1.13
    獨立
    1.09
    用意
    1.08
     পদ্ধতি
    1.07
    Util
    1.04
     diph
    1.04
     شراء
    1.03
     reutil
    1.02
     把
    1.02
    ζε
    1.00
    POSITIVE LOGITS
     lond
    0.94
     nedost
    0.93
     worsening
    0.89
     seura
    0.86
     Göl
    0.86
     pering
    0.84
    損
    0.83
     negativ
    0.83
    とな
    0.82
     Orden
    0.82
    Activations Density 0.242%

    No Known Activations