© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116210
    Prev
    Next
    INDEX
    Explanations

    imaging sequences

    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
     συμμε
    -0.07
     participa
    -0.07
    不断
    -0.07
     asympt
    -0.07
     participation
    -0.06
     условии
    -0.06
     animals
    -0.06
     свободы
    -0.06
     controlled
    -0.06
     kontroll
    -0.06
    POSITIVE LOGITS
     района
    0.07
     even
    0.07
    even
    0.06
     даже
    0.06
     "",
    0.06
     forensic
    0.06
    Even
    0.05
     הם
    0.05
     Warwickshire
    0.05
     daerah
    0.05
    Activations Density 0.007%

    No Known Activations