© 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. 117954
    Prev
    Next
    INDEX
    Explanations

    schema 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
     Previous
    -0.07
     converging
    -0.07
     apparatus
    -0.06
     preth
    -0.06
     applaud
    -0.06
     marchandises
    -0.06
    previous
    -0.06
     Pieces
    -0.06
     DATABASE
    -0.06
     protectors
    -0.06
    POSITIVE LOGITS
     в
    0.07
     на
    0.07
     sehr
    0.06
    っぽい
    0.06
     богат
    0.06
     முக
    0.06
     Everything
    0.06
     по
    0.06
     filosof
    0.05
     без
    0.05
    Activations Density 0.001%

    No Known Activations