© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 130321
    Prev
    Next
    INDEX
    Explanations

    share or contact options

    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
     которого
    -0.07
     productions
    -0.06
    ^{
    -0.06
     overclock
    -0.06
    就是一个
    -0.06
     प्योर
    -0.06
    👎
    -0.05
    하였
    -0.05
    となって
    -0.05
    Chi
    -0.05
    POSITIVE LOGITS
     for
    0.07
    ប្រើ
    0.06
     to
    0.06
     metod
    0.06
     guarding
    0.06
     iniziare
    0.06
     ഇടതു
    0.06
     स्त्रियों
    0.06
     guardar
    0.06
    anguard
    0.06
    Activations Density 0.002%

    No Known Activations