© 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. 117898
    Prev
    Next
    INDEX
    Explanations

    proto and swagger generation

    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
    ｜
    -0.07
     فایل
    -0.06
    URL
    -0.06
    alamat
    -0.06
     files
    -0.06
     aversion
    -0.06
    ↵↵↵
    -0.06
     arquivos
    -0.06
     примерно
    -0.06
     assail
    -0.05
    POSITIVE LOGITS
     absence
    0.06
     Anadolu
    0.06
     other
    0.06
    ahue
    0.06
     பேச
    0.06
    ojana
    0.06
     інших
    0.06
    不清
    0.06
     presença
    0.06
     其他
    0.06
    Activations Density 0.001%

    No Known Activations