© 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. 128315
    Prev
    Next
    INDEX
    Explanations

    competition and adjective descriptions

    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
    不
    -0.07
     مخصوص
    -0.06
    并不
    -0.06
     homage
    -0.06
     biraz
    -0.06
     特
    -0.06
    特
    -0.06
    スペシャル
    -0.06
     ничего
    -0.06
     নয়াদ
    -0.06
    POSITIVE LOGITS
     além
    0.06
     comprised
    0.06
    Trends
    0.06
     cálculo
    0.06
     oltre
    0.06
     ràng
    0.06
     sugest
    0.06
    旁的
    0.06
     তরুণ
    0.06
    oters
    0.06
    Activations Density 0.001%

    No Known Activations