© 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. 129708
    Prev
    Next
    INDEX
    Explanations

    information except

    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
     writings
    -0.06
     lessor
    -0.06
     வாய்
    -0.06
     creations
    -0.06
    BIN
    -0.06
    olok
    -0.06
     undeniable
    -0.06
     another
    -0.06
     podia
    -0.06
    läss
    -0.06
    POSITIVE LOGITS
    之间
    0.07
    初始
    0.07
    Between
    0.07
    之間
    0.06
    idual
    0.06
     initial
    0.06
    সই
    0.06
    之间的
    0.06
     між
    0.06
    間で
    0.06
    Activations Density 0.003%

    No Known Activations