© 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. 127956
    Prev
    Next
    INDEX
    Explanations

    OFDM, WAN, magnesium, what

    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
    although
    -0.08
     although
    -0.08
     aunque
    -0.07
     vaikka
    -0.07
     हालांकि
    -0.06
    aunque
    -0.06
     হলেও
    -0.06
     iako
    -0.06
    という
    -0.06
     embora
    -0.06
    POSITIVE LOGITS
     причине
    0.06
    живання
    0.06
     специально
    0.06
    参考文献
    0.06
     that
    0.05
    éci
    0.05
     einiger
    0.05
     স্বীকৃতির
    0.05
     initializes
    0.05
     pergunta
    0.05
    Activations Density 0.007%

    No Known Activations