© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130701
    Prev
    Next
    INDEX
    Explanations

    building construction, shelters, houses

    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
     Specific
    -0.07
    specific
    -0.07
     specific
    -0.06
     chín
    -0.06
    Specific
    -0.06
     systematic
    -0.06
     wró
    -0.06
    searchValue
    -0.06
     njih
    -0.06
     indicó
    -0.06
    POSITIVE LOGITS
     constructed
    0.08
     만들어
    0.07
     inadequate
    0.07
     radiates
    0.07
     crumbling
    0.06
     had
    0.06
     barely
    0.06
     Constructed
    0.06
     has
    0.06
     flimsy
    0.06
    Activations Density 0.007%

    No Known Activations