© 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. 128794
    Prev
    Next
    INDEX
    Explanations

    ethine, impure, InputField, RNA

    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
     convert
    -0.06
    但
    -0.06
     converting
    -0.06
     увеличи
    -0.06
     但
    -0.06
     деше
    -0.06
     इसी
    -0.06
     Rockies
    -0.06
    同じ
    -0.06
     distinguishing
    -0.05
    POSITIVE LOGITS
     বণ্টন
    0.06
    implantation
    0.06
    がい
    0.06
    ciudad
    0.05
    صه
    0.05
    distributed
    0.05
    ін
    0.05
     "
    0.05
    //{
    0.05
    Ἱ
    0.05
    Activations Density 0.001%

    No Known Activations