© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120107
    Prev
    Next
    INDEX
    Explanations

    which clause introducers

    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
     this
    -0.07
     any
    -0.06
     എത്ര
    -0.06
    これは
    -0.06
    这一
    -0.06
    这是
    -0.06
    这也是
    -0.06
     Đây
    -0.06
     это
    -0.06
     这是
    -0.06
    POSITIVE LOGITS
     있고
    0.07
     👇
    0.06
     👉
    0.06
    については
    0.06
    透露
    0.06
     गोपनीयता
    0.06
     standart
    0.06
    arthritis
    0.06
    founder
    0.06
     जबरदस्त
    0.06
    Activations Density 0.027%

    No Known Activations