© 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. 118153
    Prev
    Next
    INDEX
    Explanations

    increase in volumes

    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
     Ollie
    -0.07
    阻止
    -0.06
    ைகளுக்கு
    -0.06
     sucesión
    -0.06
    当然
    -0.06
    ल्‍
    -0.06
    sene
    -0.06
    minValue
    -0.06
     Clone
    -0.06
    "=
    -0.06
    POSITIVE LOGITS
     adjust
    0.07
    建議
    0.06
     विद्व
    0.06
     千
    0.06
    bajo
    0.06
    建议
    0.06
     تحت
    0.05
     adjusts
    0.05
     milliers
    0.05
     changes
    0.05
    Activations Density 0.093%

    No Known Activations