© 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. 116146
    Prev
    Next
    INDEX
    Explanations

    corporations and media companies

    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
    always
    -0.07
    Always
    -0.07
    ◆
    -0.06
    mainly
    -0.06
     transforming
    -0.06
     quickly
    -0.06
     from
    -0.06
     Always
    -0.06
    这家
    -0.06
    专注
    -0.06
    POSITIVE LOGITS
     wissenschaft
    0.06
     blots
    0.06
     investigador
    0.06
     the
    0.06
     Enrique
    0.06
     подобных
    0.06
    複数の
    0.06
    햄
    0.06
     Queensland
    0.06
     facebook
    0.06
    Activations Density 0.010%

    No Known Activations