© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 116181
    Prev
    Next
    INDEX
    Explanations

    roman numerals and chemical charges

    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
     verbunden
    -0.07
     年
    -0.06
    année
    -0.06
     下
    -0.06
     も
    -0.06
    ometimes
    -0.06
     máquina
    -0.05
    越来越
    -0.05
     burner
    -0.05
     machine
    -0.05
    POSITIVE LOGITS
     när
    0.08
     когато
    0.06
     помещения
    0.06
     пространство
    0.06
     пространства
    0.06
     lorsqu
    0.06
     các
    0.06
     όταν
    0.06
     арт
    0.06
     quando
    0.06
    Activations Density 0.007%

    No Known Activations