© 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. 116716
    Prev
    Next
    INDEX
    Explanations

    geometric projection or figure definition

    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
     leadership
    -0.06
     আমি
    -0.06
     umož
    -0.06
    $,
    -0.06
    ITEMS
    -0.06
     होईल
    -0.06
    FIRST
    -0.06
     Leadership
    -0.06
    Leadership
    -0.06
     저는
    -0.06
    POSITIVE LOGITS
     विक्रांत
    0.06
    ธิบาย
    0.06
     declaraciones
    0.06
     Breck
    0.06
     correct
    0.06
     Spaß
    0.06
     blissful
    0.06
    bindParam
    0.06
     correlating
    0.06
     제대로
    0.06
    Activations Density 0.001%

    No Known Activations