© 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. 120110
    Prev
    Next
    INDEX
    Explanations

    CPU speed and frequency

    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
    因此
    -0.07
     بنابراین
    -0.07
    wet
    -0.07
     ancienne
    -0.07
     ভয়াবহ
    -0.06
     wet
    -0.06
     Именно
    -0.06
    于是
    -0.06
    under
    -0.06
     właśnie
    -0.06
    POSITIVE LOGITS
    白色
    0.07
     accomplice
    0.06
     uncond
    0.05
     избра
    0.05
    omic
    0.05
     взрослых
    0.05
    OOSE
    0.05
    ப்பொரு
    0.05
     वय
    0.05
     separable
    0.05
    Activations Density 0.002%

    No Known Activations