© 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. 120264
    Prev
    Next
    INDEX
    Explanations

    debt, Nigerian, threatening

    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
    SizeF
    -0.07
    保護
    -0.06
     கடவு
    -0.06
    November
    -0.06
     Schutz
    -0.06
     November
    -0.06
     protectors
    -0.06
    保护
    -0.06
    شى
    -0.06
     such
    -0.05
    POSITIVE LOGITS
     respectful
    0.06
     tím
    0.06
    ഓ
    0.06
     aggressively
    0.06
     Discount
    0.06
     relentlessly
    0.06
     resurrected
    0.06
     yourself
    0.06
     ശേഖ
    0.06
    forget
    0.06
    Activations Density 0.002%

    No Known Activations