© 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. 10221
    Prev
    Next
    INDEX
    Explanations

    names starting with Van

    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
    কান্ত
    2.93
    
    2.90
    elage
    2.83
    띈
    2.83
    クリル
    2.74
    sax
    2.66
    marin
    2.65
    銖
    2.63
    sst
    2.62
    폈
    2.59
    POSITIVE LOGITS
    ЛЯ
    2.55
    組立
    2.47
     связи
    2.47
    沬
    2.46
    ী
    2.42
    렇
    2.42
     htonl
    2.41
     disrupted
    2.39
    ज्ञानिक
    2.38
    зня
    2.23
    Activations Density 0.006%

    No Known Activations