© 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. 119574
    Prev
    Next
    INDEX
    Explanations

    court citations and references

    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
     También
    -0.07
     postwar
    -0.06
     ensayo
    -0.06
     investments
    -0.06
     también
    -0.06
     आकर
    -0.06
    国際
    -0.06
     dates
    -0.06
     também
    -0.06
     सीजीएल
    -0.06
    POSITIVE LOGITS
     a
    0.06
     K
    0.05
    <0x98>
    0.05
     जनप्रतिनि
    0.05
    ণী
    0.05
     соответствующих
    0.05
    population
    0.05
     የተለያዩ
    0.05
    及其
    0.05
     تُ
    0.05
    Activations Density 0.001%

    No Known Activations