© 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. 12864
    Prev
    Next
    INDEX
    Explanations

    but more

    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
     and
    2.92
     και
    2.69
     и
    2.66
     और
    2.65
     এবং
    2.61
     và
    2.60
     आणि
    2.58
    and
    2.50
     ,
    2.39
    ,
    2.36
    POSITIVE LOGITS
    ៕
    1.62
     entsprechende
    1.22
    ֽ
    1.19
     jedynie
    1.15
     correspondingly
    1.14
     :).
    1.13
    .​​
    1.13
     ;-)
    1.13
    ALLOWED
    1.13
     }}$.
    1.12
    Activations Density 0.219%

    No Known Activations