© 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. 121032
    Prev
    Next
    INDEX
    Explanations

    as string or POSIX

    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
    包含
    -0.06
     finally
    -0.06
     endlich
    -0.06
     наконец
    -0.06
    終於
    -0.06
     finalmente
    -0.06
     هزینه
    -0.06
    终于
    -0.06
     lastly
    -0.06
    attn
    -0.06
    POSITIVE LOGITS
     in
    0.08
     fact
    0.07
     факторов
    0.06
     usw
    0.06
     sich
    0.06
    such
    0.06
     ஆறு
    0.06
     Tatsache
    0.05
     ở
    0.05
    see
    0.05
    Activations Density 0.002%

    No Known Activations