© 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. 129275
    Prev
    Next
    INDEX
    Explanations

    components and their functions

    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
     described
    -0.07
    described
    -0.07
     décrite
    -0.06
     গঠিত
    -0.06
    
    -0.06
    सरकारी
    -0.06
     cited
    -0.06
    ｳ
    -0.06
     keinen
    -0.06
     présentes
    -0.06
    POSITIVE LOGITS
     સ્થાન
    0.07
     Local
    0.07
    ّٰ
    0.07
     habe
    0.06
     hatte
    0.06
     ['$
    0.06
    eraj
    0.06
    하지만
    0.06
     }}$
    0.06
     aveva
    0.06
    Activations Density 0.040%

    No Known Activations