© 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. 128956
    Prev
    Next
    INDEX
    Explanations

    package names and licenses

    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
     you
    -0.10
     your
    -0.09
     multiple
    -0.08
     вами
    -0.07
    multiple
    -0.07
    您可以
    -0.07
    మీ
    -0.07
    あなた
    -0.07
     আপনি
    -0.07
     ваш
    -0.07
    POSITIVE LOGITS
    各
    0.06
     ம
    0.06
     அவர்களை
    0.06
     semuanya
    0.06
    状态
    0.06
     Bishop
    0.06
    控制
    0.06
     တ
    0.06
     प्रत्ये
    0.06
    材料
    0.06
    Activations Density 0.002%

    No Known Activations