© 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. 12634
    Prev
    Next
    INDEX
    Explanations

    sql SELECT FROM WHERE JOIN ON ORDER BY

    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
    Not in Any Lists

    No Comments

    Negative Logits
    けれど
    1.07
     جنب
    1.07
    лосо
    1.06
    するように
    1.05
    maz
    1.00
    CPC
    0.99
    픕
    0.98
     CIR
    0.98
    ocam
    0.97
    CAPT
    0.97
    POSITIVE LOGITS
     oder
    1.50
     atau
    1.37
    或
    1.30
     eller
    1.27
     hoặc
    1.25
     или
    1.23
     ou
    1.19
     or
    1.18
     veya
    1.17
     alebo
    1.17
    Activations Density 0.225%

    No Known Activations