© 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. 116611
    Prev
    Next
    INDEX
    Explanations

    css font-family, font-size, height

    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
    allocation
    -0.07
     সংখ
    -0.06
    শুক্রবার
    -0.06
    优先
    -0.06
    ̺
    -0.06
    সোমবার
    -0.06
    に通
    -0.06
    平台
    -0.06
    好奇
    -0.06
    ͉
    -0.06
    POSITIVE LOGITS
     using
    0.07
    :
    0.07
     वाप
    0.06
    を使用
    0.06
     gjennom
    0.06
    最终
    0.06
    vänd
    0.05
     become
    0.05
     menggunakan
    0.05
    などで
    0.05
    Activations Density 0.002%

    No Known Activations