© 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. 130134
    Prev
    Next
    INDEX
    Explanations

    install git version

    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
     nasz
    -0.07
     이걸
    -0.06
     நமது
    -0.06
     asociada
    -0.06
     이거
    -0.06
    Unsere
    -0.06
     கொஞ்சம்
    -0.06
     vezes
    -0.06
     اگر
    -0.06
     የቀ
    -0.06
    POSITIVE LOGITS
    حسن
    0.06
     già
    0.06
     initialize
    0.06
     shell
    0.06
     inital
    0.06
    أي
    0.06
     cámaras
    0.05
     ağırl
    0.05
    ইয়
    0.05
     chủ
    0.05
    Activations Density 0.001%

    No Known Activations