© 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. 116140
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming notation

    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
     inkább
    -0.06
    よりも
    -0.06
     nieco
    -0.06
    কেল
    -0.06
     година
    -0.05
     Notable
    -0.05
    ల్ని
    -0.05
     umano
    -0.05
    等が
    -0.05
     more
    -0.05
    POSITIVE LOGITS
    !!
    0.06
     Normally
    0.06
     も
    0.06
    
    0.06
     お
    0.06
     contemplated
    0.06
     भी
    0.05
     dangling
    0.05
     nd
    0.05
    如果
    0.05
    Activations Density 0.005%

    No Known Activations