© 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. 13333
    Prev
    Next
    INDEX
    Explanations

    "the conversation"

    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
    集團
    1.04
    集团
    1.01
    スペイン
    1.00
    編
    0.98
    传媒
    0.96
    荷兰
    0.96
    イヤー
    0.95
    母
    0.95
    র্ত
    0.93
    수
    0.93
    POSITIVE LOGITS
    okines
    1.10
     alken
    1.05
     Cyclone
    1.05
     cytoskeleton
    1.05
     Euph
    1.05
     titanium
    1.04
     fata
    1.04
     Же
    1.03
     tornado
    1.03
     autoclave
    1.03
    Activations Density 0.212%

    No Known Activations