© 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. 120201
    Prev
    Next
    INDEX
    Explanations

    Gene array or Romantic

    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
    ...!
    -0.07
     Biasanya
    -0.07
     boiler
    -0.06
     außen
    -0.06
     পশ্চিমে
    -0.06
    Kad
    -0.06
     Bahnhof
    -0.06
     Bismillahirrah
    -0.06
     Rudi
    -0.06
     codice
    -0.06
    POSITIVE LOGITS
     و
    0.06
     подоб
    0.06
     Wilson
    0.06
     ৭০
    0.06
     Jones
    0.06
     pudo
    0.06
     Nhưng
    0.05
     রয়ে
    0.05
     of
    0.05
     जाने
    0.05
    Activations Density 0.004%

    No Known Activations