© 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. 130193
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax

    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
     второй
    -0.06
     makes
    -0.06
     предоставляет
    -0.06
     does
    -0.06
     second
    -0.06
     itself
    -0.06
     входит
    -0.06
     ঢুক
    -0.05
    मस
    -0.05
     కొన
    -0.05
    POSITIVE LOGITS
     etc
    0.06
     während
    0.06
    scriptsize
    0.06
     Liter
    0.06
     sóc
    0.06
     সকলের
    0.06
     वेगवेगळ्या
    0.06
    さまざ
    0.06
    ద్దా
    0.06
     读取
    0.06
    Activations Density 0.002%

    No Known Activations