© 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. 115936
    Prev
    Next
    INDEX
    Explanations

    numbers followed by words

    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
     mehreren
    -0.07
     such
    -0.06
     flere
    -0.06
     разнови
    -0.06
     während
    -0.06
     multiple
    -0.06
     meerdere
    -0.06
     mehrere
    -0.06
     여러
    -0.06
     one
    -0.06
    POSITIVE LOGITS
     usually
    0.07
     geralmente
    0.07
     biasanya
    0.07
     ideally
    0.07
    usually
    0.07
     typically
    0.07
     обычно
    0.06
     Defects
    0.06
     formed
    0.06
     complementary
    0.06
    Activations Density 0.014%

    No Known Activations