© 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. 128132
    Prev
    Next
    INDEX
    Explanations

    investigation raid

    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
     ваших
    -0.06
    成分
    -0.06
     nichts
    -0.06
    RELATIVA
    -0.06
     জানার
    -0.06
    aughty
    -0.06
     neighbor
    -0.06
     nothing
    -0.06
     вашей
    -0.06
     blank
    -0.06
    POSITIVE LOGITS
     breakthrough
    0.06
    死了
    0.06
     recovered
    0.06
    هلاك
    0.06
     housekeeping
    0.06
     household
    0.06
     hızlı
    0.05
     tek
    0.05
     ፓ
    0.05
    ),
    0.05
    Activations Density 0.007%

    No Known Activations