© 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. 128130
    Prev
    Next
    INDEX
    Explanations

    created by

    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
     함께
    -0.07
     नौकरियों
    -0.06
     như
    -0.06
     generated
    -0.06
     amassed
    -0.06
     hundreds
    -0.06
    Hundreds
    -0.06
    Without
    -0.06
    迅速
    -0.06
     ರಚ
    -0.06
    POSITIVE LOGITS
    <0xE3>
    0.06
     bý
    0.06
    nye
    0.06
     Teknologi
    0.05
     важ
    0.05
     перейти
    0.05
    ையிலும்
    0.05
     valam
    0.05
     सगळे
    0.05
    を使
    0.05
    Activations Density 0.004%

    No Known Activations