© 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. 118646
    Prev
    Next
    INDEX
    Explanations

    renal, alveolar, and lobular 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
     trên
    -0.07
     volcanic
    -0.06
     dense
    -0.06
     専用
    -0.06
     डेवलप
    -0.06
     نخ
    -0.06
     criteri
    -0.06
     طب
    -0.06
     프로그램
    -0.06
     messen
    -0.06
    POSITIVE LOGITS
    inn
    0.07
     गेम्स
    0.06
     discomfort
    0.06
    ugía
    0.06
    iamond
    0.06
     liberties
    0.06
    Ag
    0.05
    opting
    0.05
     jean
    0.05
     आइये
    0.05
    Activations Density 0.025%

    No Known Activations