© 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. 130143
    Prev
    Next
    INDEX
    Explanations

    after commissionafter bedrooms

    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
    を
    -0.06
    Trader
    -0.06
     لذا
    -0.06
    AUTHENT
    -0.06
     technically
    -0.05
    に
    -0.05
     други
    -0.05
     Sod
    -0.05
    concret
    -0.05
    の
    -0.05
    POSITIVE LOGITS
     পশ্চিমা
    0.07
     after
    0.07
     With
    0.07
    หลังจาก
    0.07
     بعد
    0.07
     después
    0.06
     אחרי
    0.06
     తరువాత
    0.06
    면서
    0.06
    после
    0.06
    Activations Density 0.012%

    No Known Activations