© 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. 118748
    Prev
    Next
    INDEX
    Explanations

    environmental benign

    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
     denitr
    -0.07
    以及
    -0.06
    产品的
    -0.06
     সিংহের
    -0.06
     oraz
    -0.06
     sowie
    -0.06
    ᄌ
    -0.06
     caused
    -0.06
     કારણે
    -0.06
     ಹಾಗೂ
    -0.06
    POSITIVE LOGITS
     famed
    0.07
    RSSI
    0.07
     renowned
    0.06
    jumpa
    0.06
    嘅
    0.06
     infamous
    0.06
     utilizada
    0.06
     मूवी
    0.06
     然后
    0.06
    বিশিষ্ট
    0.05
    Activations Density 0.004%

    No Known Activations