© 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. 128164
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and structures

    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
     consecutively
    -0.06
     multiple
    -0.06
    两侧
    -0.06
     lengthy
    -0.06
    item
    -0.06
     लेकर
    -0.06
     thickly
    -0.06
    家里
    -0.06
     thoroughly
    -0.06
     final
    -0.06
    POSITIVE LOGITS
     bunların
    0.07
     advertis
    0.07
     normales
    0.06
     increase
    0.06
     publicidad
    0.06
     bleed
    0.06
     neoc
    0.06
     всегда
    0.06
    Sometimes
    0.06
     would
    0.06
    Activations Density 0.004%

    No Known Activations