© 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. 130473
    Prev
    Next
    INDEX
    Explanations

    social media

    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
     দেয়া
    -0.06
     kelahiran
    -0.06
     сказа
    -0.06
     sifatida
    -0.06
    Fprintf
    -0.06
     noma
    -0.05
    کنش
    -0.05
     gold
    -0.05
    gold
    -0.05
    fifty
    -0.05
    POSITIVE LOGITS
     quelli
    0.06
     bı
    0.06
     mał
    0.06
    之地
    0.06
     meandering
    0.06
    뽀
    0.06
     evaluator
    0.06
     blant
    0.06
    ))*(
    0.06
     stvari
    0.06
    Activations Density 0.011%

    No Known Activations