© 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. 118164
    Prev
    Next
    INDEX
    Explanations

    through the

    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
    ሽን
    -0.07
    extent
    -0.06
    if
    -0.06
    inher
    -0.06
     setelah
    -0.06
     if
    -0.06
    portion
    -0.05
     ###
    -0.05
     make
    -0.05
     touch
    -0.05
    POSITIVE LOGITS
     사람
    0.07
     প্রোগ্রাম
    0.07
     DIFFERENT
    0.06
     estaba
    0.06
     bestseller
    0.06
    :'',
    0.06
     estaban
    0.06
     funciones
    0.06
     国産
    0.06
     दुनियाभर
    0.06
    Activations Density 0.001%

    No Known Activations