© 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. 128432
    Prev
    Next
    INDEX
    Explanations

    phrase before `and`, `navy`, `island`, `kept`, `rebellion`, `Amor`

    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
     попы
    -0.07
     attempts
    -0.07
     tries
    -0.07
     intentar
    -0.07
     ప్రయత్
    -0.06
     intento
    -0.06
    しています
    -0.06
     пыта
    -0.06
     tente
    -0.06
     versucht
    -0.06
    POSITIVE LOGITS
     letzt
    0.06
     особа
    0.06
     मात
    0.06
    筹
    0.06
     могат
    0.06
    Balancer
    0.06
     हुन
    0.06
     intrigue
    0.05
     strategy
    0.05
     القسم
    0.05
    Activations Density 0.030%

    No Known Activations