© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119048
    Prev
    Next
    INDEX
    Explanations

    quasi-experimental study design

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ບໍ່
    -0.09
     không
    -0.08
     não
    -0.08
     tidak
    -0.08
     нынеш
    -0.07
     Accordingly
    -0.07
    どのような
    -0.07
     quelles
    -0.07
    하지
    -0.07
     ikke
    -0.07
    POSITIVE LOGITS
    「
    0.06
    se
    0.06
    ◆
    0.06
    様専用
    0.06
     Defines
    0.06
    “
    0.06
    ；
    0.06
     bø
    0.05
    optional
    0.05
     মাননীয়
    0.05
    Activations Density 0.005%

    No Known Activations