© 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. 128983
    Prev
    Next
    INDEX
    Explanations

    function or variable names

    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
     Such
    -0.06
     liberally
    -0.05
     bạc
    -0.05
    同样的
    -0.05
     before
    -0.05
    但在
    -0.05
     casualty
    -0.05
     burning
    -0.05
     biodivers
    -0.05
     perhaps
    -0.05
    POSITIVE LOGITS
     ohne
    0.07
     merupakan
    0.07
     tanpa
    0.06
     और
    0.06
    Otro
    0.06
    formatting
    0.06
     moniker
    0.06
     từ
    0.06
     weiteres
    0.06
     από
    0.06
    Activations Density 0.002%

    No Known Activations