© 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. 129428
    Prev
    Next
    INDEX
    Explanations

    store gallery community

    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
     ਨਹੀਂ
    -0.07
     българ
    -0.07
     भारतीय
    -0.06
     análise
    -0.06
    ตรวจ
    -0.06
     pemeriksaan
    -0.06
    ขณะ
    -0.06
     future
    -0.06
     damage
    -0.06
    future
    -0.06
    POSITIVE LOGITS
     Creations
    0.06
     lét
    0.06
     நல்ல
    0.06
     popol
    0.06
     বহুম
    0.06
    スナー
    0.06
     wereld
    0.06
     spinner
    0.06
     crafted
    0.06
    Spinner
    0.05
    Activations Density 0.004%

    No Known Activations