© 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. 117826
    Prev
    Next
    INDEX
    Explanations

    URLs containing numbers

    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
    、
    -0.07
    在
    -0.07
    の
    -0.07
    が
    -0.06
    setStatus
    -0.06
     Countdown
    -0.06
     dando
    -0.06
    要
    -0.06
     peacock
    -0.06
     пере
    -0.06
    POSITIVE LOGITS
     tiga
    0.06
     tiene
    0.06
     helps
    0.06
     specially
    0.06
     আমরা
    0.06
     protects
    0.06
     supports
    0.06
     avec
    0.06
     environmental
    0.06
     对
    0.06
    Activations Density 0.004%

    No Known Activations