© 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. 116370
    Prev
    Next
    INDEX
    Explanations

    sys_read, sys_write, sys_open

    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
     மூன்றாவது
    -0.06
    ほうが
    -0.06
     seguimos
    -0.06
    面白い
    -0.06
     своими
    -0.06
     haline
    -0.06
    uyoruz
    -0.06
    𝘱
    -0.06
     nouveaux
    -0.06
    座椅
    -0.06
    POSITIVE LOGITS
     Zugriff
    0.06
     speaking
    0.06
    Speaking
    0.05
    joe
    0.05
     asking
    0.05
     use
    0.05
     K
    0.05
     inscrit
    0.05
     관심을
    0.05
     मुख्य
    0.05
    Activations Density 0.001%

    No Known Activations