© 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. 119998
    Prev
    Next
    INDEX
    Explanations

    rounding numbers

    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
    🔭
    -0.06
     OTHER
    -0.06
    initializing
    -0.05
     精
    -0.05
    ↵
    -0.05
    მ
    -0.05
    变量
    -0.05
     otra
    -0.05
     cambiare
    -0.05
     הסי
    -0.05
    POSITIVE LOGITS
     अनुभव
    0.07
     Grenzen
    0.06
     These
    0.06
     often
    0.06
    гах
    0.06
     ausdr
    0.06
     അവരുടെ
    0.06
     remplir
    0.06
     maritime
    0.06
     경험
    0.06
    Activations Density 0.005%

    No Known Activations