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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130700
    Prev
    Next
    INDEX
    Explanations

    ages, maker, Chelsea,nonsense

    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
     continuar
    -0.07
     itself
    -0.06
     redesigned
    -0.06
     کھیلوں
    -0.06
     continuación
    -0.06
     lost
    -0.06
     also
    -0.06
     शतरंज
    -0.06
     också
    -0.06
     тоже
    -0.06
    POSITIVE LOGITS
    この
    0.07
     surtout
    0.07
    With
    0.06
    Dengan
    0.06
     समीप
    0.06
     ㄴ
    0.06
     الموا
    0.06
     संबंधित
    0.06
    From
    0.06
    ↵
    0.06
    Activations Density 0.006%

    No Known Activations