© 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. 117810
    Prev
    Next
    INDEX
    Explanations

    module imports and code structures

    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
     getting
    -0.06
     noteworthy
    -0.06
    塑造
    -0.06
     evitando
    -0.06
    ້ອງ
    -0.06
     creating
    -0.06
     만드는
    -0.06
     {})
    -0.06
     પોતાના
    -0.06
     tức
    -0.06
    POSITIVE LOGITS
    に基づ
    0.07
     гиб
    0.06
     ciertos
    0.06
    推理
    0.06
    者の
    0.06
     autosomal
    0.06
    currently
    0.06
     tenor
    0.06
     otros
    0.05
    者は
    0.05
    Activations Density 0.054%

    No Known Activations