© 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. 120574
    Prev
    Next
    INDEX
    Explanations

    when

    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
    ढ
    -0.07
    と同じ
    -0.06
    সাল
    -0.06
     احنا
    -0.06
     our
    -0.06
    จาก
    -0.06
    我們
    -0.06
    Ɗ
    -0.06
     हम
    -0.06
    我们
    -0.06
    POSITIVE LOGITS
     disadvantages
    0.07
     puede
    0.07
     Gdy
    0.07
     drawback
    0.07
     gdy
    0.06
     remain
    0.06
     lorsque
    0.06
     restent
    0.06
    puede
    0.06
     pioneers
    0.06
    Activations Density 0.022%

    No Known Activations