© 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. 120184
    Prev
    Next
    INDEX
    Explanations

    mathematical variables often followed 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
    Not in Any Lists

    No Comments

    Negative Logits
     complained
    -0.07
     complain
    -0.07
    $-$,
    -0.06
    おすすめ
    -0.06
    도가
    -0.06
     cuyos
    -0.06
     
    -0.06
    隙
    -0.06
    امة
    -0.06
    ধর্ম
    -0.06
    POSITIVE LOGITS
     patrimonio
    0.06
     again
    0.06
     identical
    0.06
     মাথায়
    0.06
     patrimoine
    0.05
     Koy
    0.05
     উদ্বাস্তু
    0.05
    மிழ்
    0.05
    Taste
    0.05
     settles
    0.05
    Activations Density 0.001%

    No Known Activations