© 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. 120286
    Prev
    Next
    INDEX
    Explanations

    transradial access

    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
     любую
    -0.07
     herhangi
    -0.06
     contraband
    -0.06
     ubicada
    -0.06
     gleichen
    -0.06
    成員
    -0.06
     клиент
    -0.06
     outcry
    -0.06
    กล้
    -0.06
     klient
    -0.06
    POSITIVE LOGITS
    For
    0.06
     selle
    0.06
    loos
    0.05
     مقامی
    0.05
    不大
    0.05
    それぞれの
    0.05
    更加
    0.05
     skulls
    0.05
     BDS
    0.05
     
    0.05
    Activations Density 0.018%

    No Known Activations