© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130777
    Prev
    Next
    INDEX
    Explanations

    Enabler, Influence, Reflexion, Excel

    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
    こちらも
    -0.07
     fashioned
    -0.06
     implementations
    -0.06
     challenges
    -0.06
    จาก
    -0.06
     Informations
    -0.06
    ទៀត
    -0.06
     OMC
    -0.06
    zone
    -0.06
    關於
    -0.06
    POSITIVE LOGITS
    British
    0.06
     इसलिये
    0.06
     ब्रिटिश
    0.06
     உயர்
    0.06
    णारे
    0.06
    utenção
    0.06
     अंग्रेजों
    0.06
     British
    0.06
     ব্রিটিশ
    0.06
     الجما
    0.05
    Activations Density 0.001%

    No Known Activations