© 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. 116194
    Prev
    Next
    INDEX
    Explanations

    vb.net code declarations

    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
    utia
    -0.07
     modest
    -0.06
    下图
    -0.06
    ;
    -0.06
    .
    -0.06
    如下图
    -0.06
    एक
    -0.06
     whereof
    -0.06
    urist
    -0.05
     sammen
    -0.05
    POSITIVE LOGITS
     our
    0.07
     नामित
    0.06
    Stability
    0.06
     Mullins
    0.06
    Unsere
    0.06
     officially
    0.06
    ococcus
    0.06
     unsere
    0.06
     Params
    0.06
     وجه
    0.06
    Activations Density 0.011%

    No Known Activations