© 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. 119219
    Prev
    Next
    INDEX
    Explanations

    recommendations or suggestions

    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
    blown
    -0.07
    ILY
    -0.07
    ploy
    -0.06
    這樣的
    -0.06
     있는데요
    -0.06
    这样的
    -0.06
     такой
    -0.06
    অপর
    -0.06
     χρει
    -0.06
    Mer
    -0.06
    POSITIVE LOGITS
     maybe
    0.07
     추천
    0.07
    オススメ
    0.07
     antigos
    0.06
     must
    0.06
     mógł
    0.06
     qualsiasi
    0.06
     mungkin
    0.06
    អាច
    0.06
     could
    0.06
    Activations Density 0.015%

    No Known Activations