© 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. 128063
    Prev
    Next
    INDEX
    Explanations

    .csproj", ".h", ".mh"

    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
     kuidas
    -0.08
     және
    -0.07
     मेकअप
    -0.07
    न्त
    -0.06
     sesión
    -0.06
    블
    -0.06
    izzate
    -0.06
    ফ
    -0.06
     אך
    -0.06
    の名前
    -0.06
    POSITIVE LOGITS
     as
    0.08
     another
    0.06
     such
    0.06
    another
    0.05
     Thomas
    0.05
     love
    0.05
    amyl
    0.05
     larger
    0.05
     जॉन
    0.05
     Canadian
    0.05
    Activations Density 0.005%

    No Known Activations