© 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. 129555
    Prev
    Next
    INDEX
    Explanations

    code, programming structure

    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
    ühm
    -0.06
    英雄
    -0.06
    potentially
    -0.06
     anhand
    -0.06
    ?).
    -0.06
     আহম্মদ
    -0.06
     собрать
    -0.06
     freshwater
    -0.06
    cars
    -0.05
     ఇందులో
    -0.05
    POSITIVE LOGITS
    ↵
    0.07
     وقتی
    0.07
     когато
    0.07
     quando
    0.07
     lorsque
    0.06
    以及
    0.06
     obtaining
    0.06
    
    0.06
     عندما
    0.06
    妨
    0.06
    Activations Density 0.004%

    No Known Activations