© 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. 128102
    Prev
    Next
    INDEX
    Explanations

    database operations

    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
     ordnance
    -0.07
    bss
    -0.06
     integers
    -0.06
    Variable
    -0.06
     homicide
    -0.06
     variable
    -0.06
    ాను
    -0.06
    number
    -0.06
    playSound
    -0.06
    Function
    -0.06
    POSITIVE LOGITS
     from
    0.08
     desde
    0.07
     on
    0.06
    തിൽ
    0.06
     quietly
    0.06
     từ
    0.06
     från
    0.06
     en
    0.06
     smarter
    0.06
     în
    0.06
    Activations Density 0.010%

    No Known Activations