© 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. 117402
    Prev
    Next
    INDEX
    Explanations

    granted or issued with documents

    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
     저는
    -0.07
     create
    -0.06
     successfully
    -0.06
     তিনি
    -0.06
     utilizzare
    -0.06
    Three
    -0.06
     приобрести
    -0.06
     他
    -0.06
     meticulously
    -0.06
    successfully
    -0.06
    POSITIVE LOGITS
    グラ
    0.06
    Expl
    0.06
     stillness
    0.05
     dř
    0.05
     স্বদেশ
    0.05
     뒤
    0.05
     Refugee
    0.05
    旅游
    0.05
     horror
    0.05
    下一
    0.05
    Activations Density 0.008%

    No Known Activations