© 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. 118417
    Prev
    Next
    INDEX
    Explanations

    if ... then

    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
     регулярно
    -0.07
     yoj
    -0.06
     venu
    -0.06
     ниже
    -0.06
     ವಿದ
    -0.06
     noten
    -0.06
     brainchild
    -0.06
    木
    -0.06
     inicios
    -0.06
     자기
    -0.06
    POSITIVE LOGITS
     yes
    0.07
    Yes
    0.06
     etc
    0.06
     alcanz
    0.06
    gap
    0.06
     sẽ
    0.06
    เป
    0.06
     differences
    0.06
     Yes
    0.06
    等着
    0.06
    Activations Density 0.044%

    No Known Activations