© 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. 130202
    Prev
    Next
    INDEX
    Explanations

    asymptotic

    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
    ometime
    -0.07
     постепенно
    -0.07
     quiescent
    -0.06
     transition
    -0.06
    完成后
    -0.06
     warm
    -0.06
     transición
    -0.06
     shudder
    -0.06
    obviously
    -0.06
    Transition
    -0.06
    POSITIVE LOGITS
     requirement
    0.06
    हून
    0.06
     requisitos
    0.06
     forehead
    0.06
     देखा
    0.06
     musste
    0.06
    ギター
    0.06
    ждение
    0.06
     micrographs
    0.06
     Daniel
    0.06
    Activations Density 0.003%

    No Known Activations