© 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. 129596
    Prev
    Next
    INDEX
    Explanations

    From Until Late

    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
     ছাড়াও
    -0.07
     oltre
    -0.07
     sollen
    -0.06
     افراد
    -0.06
    点
    -0.06
     prompting
    -0.06
     помогают
    -0.06
     లు
    -0.06
     adage
    -0.06
     पाण्डेय
    -0.06
    POSITIVE LOGITS
     гораздо
    0.06
    !
    0.06
     какой
    0.06
     far
    0.06
    目前
    0.06
    маты
    0.06
     такой
    0.06
    십시오
    0.05
     Elegant
    0.05
     yourself
    0.05
    Activations Density 0.014%

    No Known Activations