© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 128561
    Prev
    Next
    INDEX
    Explanations

    package declarations

    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
     lieu
    -0.06
     گاه
    -0.06
    有些人
    -0.05
     suficiente
    -0.05
     apie
    -0.05
     obwohl
    -0.05
    ፣
    -0.05
     आपको
    -0.05
     exclusive
    -0.05
     supple
    -0.05
    POSITIVE LOGITS
     for
    0.06
    More
    0.06
     বাইরে
    0.06
     inklusive
    0.06
    Atual
    0.06
     வெளிய
    0.06
     inscriptions
    0.06
     intérêts
    0.06
    িতে
    0.06
     برای
    0.06
    Activations Density 0.001%

    No Known Activations