© 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. 2787
    Prev
    Next
    INDEX
    Explanations

    PHP plugin code descriptions

    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
     亠
    2.00
     AGEN
    1.92
     ロゴ
    1.87
     ị
    1.87
     売場面積
    1.85
    硏
    1.85
     tileSize
    1.83
     Mauer
    1.82
     村
    1.80
     리뷰
    1.79
    POSITIVE LOGITS
    that
    1.31
    time
    1.30
    tos
    1.28
    and
    1.27
    the
    1.25
    tt
    1.23
    ↵
    1.22
    tet
    1.20
    tti
    1.17
    vous
    1.13
    Activations Density 0.004%

    No Known Activations