© 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. 121001
    Prev
    Next
    INDEX
    Explanations

    trivial tasks

    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
     any
    -0.07
     your
    -0.07
     ذخ
    -0.06
     future
    -0.06
     stored
    -0.06
     either
    -0.06
     myof
    -0.06
     Dzięki
    -0.06
    fifo
    -0.05
    })(\
    -0.05
    POSITIVE LOGITS
     bezpośred
    0.08
     directo
    0.07
     直接
    0.07
    Already
    0.07
    直接
    0.07
     simpel
    0.07
     его
    0.06
     crappy
    0.06
     иногда
    0.06
     بسيط
    0.06
    Activations Density 0.041%

    No Known Activations