© 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. 4011
    Prev
    Next
    INDEX
    Explanations

    grand and privileges

    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
    bn
    1.77
    heavy
    1.63
    льки
    1.61
    cont
    1.56
    ed
    1.52
    叽
    1.51
    with
    1.51
    and
    1.50
    qu
    1.50
    <bos>
    1.50
    POSITIVE LOGITS
    ीकरण
    2.40
    ी
    2.09
     republik
    1.96
     SalesLT
    1.93
     επέ
    1.91
    宿
    1.90
     tarif
    1.90
     introducir
    1.87
     ingresar
    1.86
    ㄢ
    1.85
    Activations Density 0.075%

    No Known Activations