© 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. 118442
    Prev
    Next
    INDEX
    Explanations

    prior art

    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
    нных
    -0.06
     대한
    -0.06
     classific
    -0.05
     maintenir
    -0.05
    년을
    -0.05
    sinh
    -0.05
     لأنه
    -0.05
    我对
    -0.05
    他对
    -0.05
     ಹಾಕ
    -0.05
    POSITIVE LOGITS
    Super
    0.06
     ইতি
    0.06
    院
    0.06
    riding
    0.06
     as
    0.06
     محمد
    0.06
    rictor
    0.06
     тот
    0.05
    भाषा
    0.05
     Super
    0.05
    Activations Density 0.003%

    No Known Activations