© 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. 120057
    Prev
    Next
    INDEX
    Explanations

    period or term of years

    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
    五
    -0.06
     되
    -0.06
     rather
    -0.06
     uzun
    -0.06
    整个
    -0.06
     vijf
    -0.06
    utilisateur
    -0.06
     využ
    -0.06
     fünf
    -0.06
     পাঁচটি
    -0.06
    POSITIVE LOGITS
     недавно
    0.07
    готов
    0.06
     mower
    0.06
    日に
    0.06
     ironically
    0.06
     июле
    0.06
     hace
    0.06
    开启
    0.06
     intermediaries
    0.05
    Так
    0.05
    Activations Density 0.005%

    No Known Activations