© 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. 118094
    Prev
    Next
    INDEX
    Explanations

    Google SEO optimization

    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
     it
    -0.07
     típico
    -0.06
    relu
    -0.06
    却是
    -0.06
    ละคร
    -0.06
    lund
    -0.06
     wordArray
    -0.06
     jsem
    -0.06
     risultati
    -0.06
     ৫০
    -0.06
    POSITIVE LOGITS
    两个
    0.06
    ขั้นตอน
    0.06
     эн
    0.06
    一只
    0.06
     requirements
    0.05
    吃
    0.05
     informacija
    0.05
    エン
    0.05
     Сейчас
    0.05
    壶
    0.05
    Activations Density 0.002%

    No Known Activations