© 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. 121072
    Prev
    Next
    INDEX
    Explanations

    time reference

    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
     võib
    -0.06
     może
    -0.06
     ње
    -0.06
     mógł
    -0.06
     perhaps
    -0.06
     možda
    -0.06
     násled
    -0.06
    ುತ್ತೇವೆ
    -0.06
     belki
    -0.06
     Macbeth
    -0.05
    POSITIVE LOGITS
     is
    0.08
     heretofore
    0.08
     ngayon
    0.08
     now
    0.08
     اکنون
    0.07
     Ở
    0.07
     sekarang
    0.07
    ตอนนี้
    0.07
    不是
    0.07
     merely
    0.07
    Activations Density 0.006%

    No Known Activations