© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6556
    Prev
    Next
    INDEX
    Explanations

    where it gets interesting

    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
     therefor
    1.14
     bacilli
    1.12
    初始
    1.03
    數學
    1.02
     Toán
    1.02
     quotients
    1.01
     基本
    1.00
    初
    1.00
    -(-
    0.99
     resultant
    0.98
    POSITIVE LOGITS
    Lastly
    1.23
    another
    1.21
     Lastly
    1.19
    Another
    1.14
    incredible
    1.09
     another
    1.08
     আরেকটি
    1.05
     unglaublich
    1.03
     outro
    1.03
     Harsh
    1.02
    Activations Density 0.163%

    No Known Activations