© 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. 119265
    Prev
    Next
    INDEX
    Explanations

    but not exclusively

    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
     някои
    -0.07
     некоторых
    -0.07
     algumas
    -0.07
     sommige
    -0.07
     algunas
    -0.06
    感受到
    -0.06
    某些
    -0.06
     algunos
    -0.06
     diversos
    -0.06
     alcuni
    -0.06
    POSITIVE LOGITS
     its
    0.07
     mấy
    0.07
    sinx
    0.06
     list
    0.06
     favore
    0.06
     NASDAQ
    0.06
    its
    0.06
    その
    0.06
     NASA
    0.06
     this
    0.05
    Activations Density 0.004%

    No Known Activations