© 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. 129425
    Prev
    Next
    INDEX
    Explanations

    ask for information

    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
     khususnya
    -0.07
     ninguna
    -0.06
     terutama
    -0.06
     opportunità
    -0.06
     Asociación
    -0.06
    特に
    -0.06
    ាច
    -0.06
     குறிப்பாக
    -0.06
    specifically
    -0.06
     yrs
    -0.06
    POSITIVE LOGITS
     today
    0.07
     Important
    0.07
    Combine
    0.06
    それぞれ
    0.06
     together
    0.06
     Zudem
    0.06
     If
    0.06
     önemli
    0.06
    respective
    0.06
    ইংরেজি
    0.06
    Activations Density 0.008%

    No Known Activations