© 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. 128436
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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
    也
    -0.06
    delen
    -0.06
     Univer
    -0.06
     wichtig
    -0.06
     rebels
    -0.06
     அற்புத
    -0.06
    த்துடன்
    -0.06
     situazioni
    -0.06
     নিয়েই
    -0.05
     মানুষ
    -0.05
    POSITIVE LOGITS
     όπως
    0.06
    ம்பரிய
    0.06
    像
    0.06
     દર
    0.06
    !!!!!!!!!!!!!!!!
    0.06
     самом
    0.06
     явно
    0.06
     今
    0.06
     तोला
    0.06
     like
    0.06
    Activations Density 0.004%

    No Known Activations