© 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. 119999
    Prev
    Next
    INDEX
    Explanations

    xml attributes and import statements

    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
     tentar
    -0.07
     sogenannte
    -0.07
     infecting
    -0.07
     விச
    -0.06
     включая
    -0.06
     sogenannten
    -0.06
    を含む
    -0.06
     Appel
    -0.06
     पोहो
    -0.06
     sogar
    -0.06
    POSITIVE LOGITS
    禇
    0.06
     createUser
    0.06
     Catholics
    0.05
     videogame
    0.05
    elian
    0.05
    人气
    0.05
     according
    0.05
    هر
    0.05
    Jazz
    0.05
     এছাড়াও
    0.05
    Activations Density 0.001%

    No Known Activations