© 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. 118051
    Prev
    Next
    INDEX
    Explanations

    executable names and file paths

    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
     म
    -0.06
     argumento
    -0.06
     ack
    -0.06
     tôi
    -0.06
     followed
    -0.06
     Martian
    -0.06
     seguido
    -0.06
    сион
    -0.06
     मं
    -0.06
     graphon
    -0.06
    POSITIVE LOGITS
     mee
    0.06
    前面的
    0.06
     प्रोसे
    0.06
    凸
    0.05
    ებულ
    0.05
    เดิม
    0.05
    已被
    0.05
     scheduling
    0.05
     UBS
    0.05
    Listener
    0.05
    Activations Density 0.052%

    No Known Activations