© 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. 119109
    Prev
    Next
    INDEX
    Explanations

    author contributions

    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
     aquele
    -0.06
    癹
    -0.06
     acoustics
    -0.06
     curling
    -0.06
     Wanted
    -0.06
     Expand
    -0.06
    続きを読む
    -0.06
    essai
    -0.05
     idioma
    -0.05
     underlying
    -0.05
    POSITIVE LOGITS
     sterk
    0.06
     yapıyor
    0.06
     ίδια
    0.06
     trước
    0.06
     (=
    0.06
     before
    0.06
     mating
    0.06
     JUD
    0.05
    един
    0.05
     применяется
    0.05
    Activations Density 0.001%

    No Known Activations