© 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. 116262
    Prev
    Next
    INDEX
    Explanations

    staining pattern

    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
     again
    -0.06
     still
    -0.06
     ladies
    -0.06
    level
    -0.06
     ponownie
    -0.06
     снова
    -0.06
     பேசு
    -0.06
     kreat
    -0.06
    ando
    -0.06
     เครื่อง
    -0.06
    POSITIVE LOGITS
     gamme
    0.06
     Vasily
    0.06
     Miller
    0.06
    㳯
    0.06
    thousands
    0.06
    🐆
    0.06
    hatiti
    0.06
     વિધાનસભા
    0.06
    useppe
    0.06
     ürün
    0.06
    Activations Density 0.005%

    No Known Activations