© 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. 116035
    Prev
    Next
    INDEX
    Explanations

    assuming is positive

    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
    Negative Logits
    Usually
    -0.07
    通常
    -0.07
    常常
    -0.06
     usually
    -0.06
     accustomed
    -0.06
     conventional
    -0.06
     Usually
    -0.06
     नेहमी
    -0.06
     обычно
    -0.06
    ophilic
    -0.06
    POSITIVE LOGITS
     VARIABLE
    0.07
     कंटिन्यू
    0.07
     aniversario
    0.06
    فرق
    0.06
     शीघ्र
    0.06
     पटाखे
    0.05
     সংশোধন
    0.05
    वणे
    0.05
     nächsten
    0.05
     Female
    0.05
    Activations Density 0.001%

    No Known Activations