© 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. 130373
    Prev
    Next
    INDEX
    Explanations

    alphanumeric strings and identifiers

    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
    本来
    -0.06
    以下
    -0.06
    苞
    -0.06
     davantage
    -0.06
     измени
    -0.06
    主に
    -0.06
     прежде
    -0.06
     zj
    -0.05
     برای
    -0.05
    それ
    -0.05
    POSITIVE LOGITS
     William
    0.06
    रथ
    0.06
     where
    0.06
     dezelfde
    0.06
     samme
    0.06
     même
    0.06
     tercih
    0.06
     ਵੀ
    0.06
    dar
    0.06
     mêmes
    0.06
    Activations Density 0.012%

    No Known Activations