© 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. 121055
    Prev
    Next
    INDEX
    Explanations

    free comparison

    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
     स्वर्ग
    -0.07
    hotels
    -0.06
     SoC
    -0.06
    expenses
    -0.06
    几乎
    -0.06
     高校
    -0.06
    踴
    -0.06
     seminar
    -0.05
     fő
    -0.05
     vocês
    -0.05
    POSITIVE LOGITS
     myös
    0.07
     racer
    0.06
     Guides
    0.06
    惺
    0.06
     racing
    0.06
     anche
    0.06
     тоже
    0.06
     too
    0.06
     notable
    0.06
     também
    0.06
    Activations Density 0.007%

    No Known Activations