© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130377
    Prev
    Next
    INDEX
    Explanations

    names and places

    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
     schizophren
    -0.06
    شون
    -0.06
     jihad
    -0.06
    慑
    -0.06
    μή
    -0.06
    রাষ্ট
    -0.06
    Integrating
    -0.06
    MQTT
    -0.06
     एक्सेस
    -0.06
    andu
    -0.06
    POSITIVE LOGITS
    त्याने
    0.06
     sitcom
    0.06
     hobby
    0.06
     छोटे
    0.06
     comeback
    0.06
     countryside
    0.06
    *%
    0.06
     বিশ্বের
    0.06
     unseen
    0.06
     Genuine
    0.06
    Activations Density 0.005%

    No Known Activations