© 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. 3957
    Prev
    Next
    INDEX
    Explanations

    Drake Equation

    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
     Hàn
    1.87
    雙
    1.85
     شورای
    1.81
    韓
    1.81
    스테
    1.77
    카페
    1.74
     HANA
    1.74
     CBI
    1.71
    ハン
    1.68
    ブリ
    1.64
    POSITIVE LOGITS
    <strong>
    1.62
    ّ
    1.61
    <h2>
    1.52
    Leary
    1.52
    Bodies
    1.51
    Objectives
    1.51
    Tut
    1.50
    nemis
    1.49
    َّ
    1.49
    Ent
    1.45
    Activations Density 0.027%

    No Known Activations