© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117167
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     afterthought
    -0.06
     LOCAL
    -0.06
     announced
    -0.06
    勁
    -0.06
     এসব
    -0.06
     and
    -0.06
     स्किन
    -0.06
     পঞ্চম
    -0.05
     advised
    -0.05
     assignments
    -0.05
    POSITIVE LOGITS
     coinciding
    0.07
     우리가
    0.07
     quand
    0.07
     keadaan
    0.06
     Quand
    0.06
     भंडारण
    0.06
    Quand
    0.06
     preceding
    0.06
     éste
    0.06
    時には
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.