© 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. 119643
    Prev
    Next
    INDEX
    Explanations

    .ctrl SET

    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
    !..
    -0.07
     vigente
    -0.06
    🏃
    -0.06
     бывают
    -0.06
     çeşit
    -0.06
     lalu
    -0.06
     ingin
    -0.06
    一つの
    -0.06
     the
    -0.06
    POSITIVE LOGITS
     ensu
    0.06
     সেই
    0.06
     if
    0.06
     verwendeten
    0.06
    ikuti
    0.05
    metic
    0.05
     textAlign
    0.05
     يأ
    0.05
     தண்ட
    0.05
     diğer
    0.05
    Activations Density 0.004%

    No Known Activations