© 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. 116972
    Prev
    Next
    INDEX
    Explanations

    citation labels

    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
     म्हणजेच
    -0.07
     পিপ
    -0.06
     genomic
    -0.05
     पोस्टम
    -0.05
     conhecida
    -0.05
     wore
    -0.05
     वाइ
    -0.05
     참
    -0.05
     poter
    -0.05
     vines
    -0.05
    POSITIVE LOGITS
     таки
    0.07
     автофо
    0.06
     away
    0.06
     permettent
    0.06
     мене
    0.06
    מבר
    0.06
     Campan
    0.06
     गायब
    0.06
     On
    0.06
    TakePhoto
    0.06
    Activations Density 0.004%

    No Known Activations