© 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. 120169
    Prev
    Next
    INDEX
    Explanations

    tax

    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
     alternate
    -0.07
    A
    -0.06
     pouze
    -0.06
     आयुष
    -0.06
    ý
    -0.06
     tetanus
    -0.06
     skateboard
    -0.05
     A
    -0.05
     skateboarding
    -0.05
     momentous
    -0.05
    POSITIVE LOGITS
     detects
    0.07
    税
    0.07
     détecter
    0.07
     pagamento
    0.07
    收款
    0.07
     информация
    0.07
     налого
    0.07
    Identifying
    0.07
     facilmente
    0.07
     поиск
    0.07
    Activations Density 0.003%

    No Known Activations