© 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. 116978
    Prev
    Next
    INDEX
    Explanations

    television networks

    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
     ballads
    -0.07
     iniz
    -0.07
    と思
    -0.07
    france
    -0.06
     гораздо
    -0.06
     سایټ
    -0.06
    renown
    -0.06
    テーマ
    -0.06
     tutto
    -0.06
     Cá
    -0.06
    POSITIVE LOGITS
     exige
    0.06
     потребо
    0.06
     požad
    0.06
     ترتیب
    0.06
    Ii
    0.06
     Video
    0.06
     incriminating
    0.06
    Video
    0.06
     becomes
    0.06
     materials
    0.05
    Activations Density 0.002%

    No Known Activations