© 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. 116154
    Prev
    Next
    INDEX
    Explanations

    patent application numbers

    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
    所以
    -0.07
    其
    -0.07
     hips
    -0.07
    需要
    -0.06
     want
    -0.06
    但是
    -0.06
    關於
    -0.06
    可以
    -0.06
     CASES
    -0.06
     These
    -0.06
    POSITIVE LOGITS
     όλ
    0.06
    -
    0.06
     beim
    0.06
     fairly
    0.06
     naïve
    0.06
     virtually
    0.06
     environmentally
    0.06
     energetic
    0.06
     lengthy
    0.05
    '),
    0.05
    Activations Density 0.006%

    No Known Activations