© 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. 129676
    Prev
    Next
    INDEX
    Explanations

    names, Q: questions

    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
    ñ
    -0.06
    Implicit
    -0.06
    spirit
    -0.06
     Trag
    -0.06
     hiểu
    -0.06
     Фа
    -0.06
    Inicial
    -0.06
    ръ
    -0.06
     সফরে
    -0.05
     aceasta
    -0.05
    POSITIVE LOGITS
     celé
    0.07
     seluruh
    0.07
     especially
    0.06
     oppose
    0.06
    ല്ലാത്ത
    0.06
    ન્
    0.06
     periodically
    0.06
    尤其是
    0.06
     intervenir
    0.06
    ulièrement
    0.06
    Activations Density 0.004%

    No Known Activations