© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128276
    Prev
    Next
    INDEX
    Explanations

    fs

    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
     With
    -0.07
     કરતાં
    -0.06
     ಅತ್ಯ
    -0.06
     মাম
    -0.06
     với
    -0.06
     给
    -0.06
    निम्नलिखित
    -0.06
     đáp
    -0.06
     kepentingan
    -0.06
     тому
    -0.06
    POSITIVE LOGITS
     apoptotic
    0.06
     these
    0.06
    ตรวจ
    0.06
     ऑफलाइन
    0.06
    rische
    0.06
     مانند
    0.06
    otte
    0.06
     may
    0.06
    ოგ
    0.06
    ۈ
    0.06
    Activations Density 0.001%

    No Known Activations