© 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. 3970
    Prev
    Next
    INDEX
    Explanations

    howstuffworks.com and fool.com

    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
    Zeneca
    2.14
    yacute
    1.75
    ́n
    1.65
    hip
    1.64
    बान
    1.60
    romes
    1.58
    
    1.56
     의한
    1.56
    …”
    1.53
    incorpor
    1.50
    POSITIVE LOGITS
    𝘱
    2.14
    د
    2.07
    စဉ်
    2.05
    სა
    2.02
    𝘳
    2.00
     %%
    1.97
    ｪ
    1.97
    tudo
    1.90
     pyl
    1.89
    ОВО
    1.89
    Activations Density 0.030%

    No Known Activations