© 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. 116930
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     どう
    -0.06
     fullest
    -0.06
     конкре
    -0.06
     Canadian
    -0.06
     perils
    -0.06
     NOI
    -0.06
     sponsoring
    -0.06
     konkrét
    -0.06
     betterment
    -0.06
     Phát
    -0.06
    POSITIVE LOGITS
    其中
    0.06
    中断
    0.06
     for
    0.06
    而
    0.05
     오히려
    0.05
     няколко
    0.05
    ():
    0.05
    ко
    0.05
    ത്തിൽ
    0.05
     bereits
    0.05
    Activations Density 0.043%

    No Known Activations