© 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. 13186
    Prev
    Next
    INDEX
    Explanations

    specific relations and entities

    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
    1.50
    וה
    1.20
    ו
    1.15
     和
    1.12
     ও
    1.10
    、
    1.10
    および
    1.09
    录
    1.08
     ಮತ್ತು
    1.08
    和
    1.06
    POSITIVE LOGITS
    otros
    1.56
    Turb
    1.49
    תיים
    1.49
    Neur
    1.48
    Ack
    1.48
    ión
    1.47
    Prod
    1.46
    Bsky
    1.44
    ácil
    1.44
    Collapse
    1.43
    Activations Density 0.000%

    No Known Activations