© 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. 12983
    Prev
    Next
    INDEX
    Explanations

    image and code fragments

    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
    ăș
    2.22
    ș
    2.12
    și
    2.08
    colorful
    2.06
    Ș
    2.00
    theater
    1.95
     lackluster
    1.95
    нё
    1.92
    flavored
    1.90
    jewelry
    1.90
    POSITIVE LOGITS
     realise
    2.15
     Whilst
    2.14
     recognise
    2.12
     minimise
    2.10
     visualise
    2.07
     maximise
    2.03
     emphasise
    2.00
     recognises
    1.93
    ﯿ
    1.90
     recognising
    1.90
    Activations Density 0.021%

    No Known Activations