© 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. 128155
    Prev
    Next
    INDEX
    Explanations

    programming libraries and code

    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
     schließlich
    -0.06
     soprattutto
    -0.06
     Albuquerque
    -0.06
     kerana
    -0.06
    sensitive
    -0.06
     etwa
    -0.06
     Maybe
    -0.06
    marginBottom
    -0.06
     cambiando
    -0.06
    maybe
    -0.06
    POSITIVE LOGITS
     qualifies
    0.06
     while
    0.06
     increased
    0.06
     represents
    0.06
    irken
    0.06
     representation
    0.06
     ശാഫിഈ
    0.06
     sosial
    0.06
    पटॉप
    0.06
     فوتب
    0.06
    Activations Density 0.009%

    No Known Activations