© 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. 13182
    Prev
    Next
    INDEX
    Explanations

    "BlueprintFlow" is fascinating

    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
     glLightfv
    1.47
     colegio
    1.39
     principalTable
    1.38
     قوانین
    1.37
    <unused1277>
    1.37
    哫
    1.36
     यातायात
    1.36
    ValueLayout
    1.35
    ጐ
    1.33
     glLight
    1.33
    POSITIVE LOGITS
     never
    0.91
    从未
    0.88
     tr
    0.85
    ized
    0.83
     launch
    0.82
     r
    0.82
     final
    0.82
     "
    0.80
     mon
    0.79
    0.77
    Activations Density 0.001%

    No Known Activations