© 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. 128537
    Prev
    Next
    INDEX
    Explanations

    display devices

    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
     поги
    -0.06
    女の子
    -0.06
     syrups
    -0.06
    摄像
    -0.06
     песен
    -0.06
     necesarias
    -0.06
     ence
    -0.06
     गाली
    -0.06
     کسی
    -0.06
    เลข
    -0.06
    POSITIVE LOGITS
     gentle
    0.07
     unchanging
    0.07
     representing
    0.06
    two
    0.06
     ताजा
    0.06
     જૂ
    0.06
     ফিরিয়ে
    0.06
     ቀላል
    0.06
     Gentle
    0.06
     refreshing
    0.06
    Activations Density 0.005%

    No Known Activations