© 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. 119933
    Prev
    Next
    INDEX
    Explanations

    execution

    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
     این
    -0.10
     from
    -0.10
     to
    -0.09
     this
    -0.08
     هذا
    -0.08
    這個
    -0.08
     этот
    -0.08
    這
    -0.08
     এই
    -0.08
     Nonetheless
    -0.08
    POSITIVE LOGITS
    を
    0.07
     (
    0.07
     wobei
    0.07
    을
    0.06
    に
    0.06
    ,
    0.06
    ซึ่ง
    0.06
    를
    0.06
    が
    0.06
    ㅎ
    0.06
    Activations Density 0.006%

    No Known Activations