© 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. 120330
    Prev
    Next
    INDEX
    Explanations

    federal agency, radiograph

    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
    †
    -0.06
     herhangi
    -0.06
     contribution
    -0.06
    任意の
    -0.06
     dowol
    -0.05
    ز
    -0.05
     DISNEY
    -0.05
     significant
    -0.05
     และ
    -0.05
    OUND
    -0.05
    POSITIVE LOGITS
    chomp
    0.06
    天氣
    0.06
     despite
    0.06
     emociones
    0.06
    放入
    0.06
     регуляр
    0.06
     it
    0.06
    には
    0.06
     deviceInfo
    0.06
    에는
    0.06
    Activations Density 0.001%

    No Known Activations