© 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. 117444
    Prev
    Next
    INDEX
    Explanations

    list items or code structure

    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
    哪個
    -0.07
     మనం
    -0.07
     ಅಥವಾ
    -0.07
    我们可以
    -0.07
     podemos
    -0.06
     आपकी
    -0.06
    我們可以
    -0.06
     glorious
    -0.06
     あなた
    -0.06
    ulence
    -0.06
    POSITIVE LOGITS
    )
    0.07
    ).
    0.06
     проблемой
    0.06
     taip
    0.06
    절
    0.06
    จึง
    0.06
    jim
    0.06
     remain
    0.06
     crist
    0.06
    如下
    0.06
    Activations Density 0.005%

    No Known Activations