© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118211
    Prev
    Next
    INDEX
    Explanations

    section markers

    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
     soğ
    -0.07
     với
    -0.06
     חיצוני
    -0.06
     различных
    -0.06
     દ્વારા
    -0.06
     soprattutto
    -0.06
    ᱶ
    -0.06
     နဲ့
    -0.06
     документов
    -0.06
     attraverso
    -0.06
    POSITIVE LOGITS
     the
    0.06
     pembahasan
    0.06
     to
    0.06
    വിന്
    0.06
    Column
    0.06
     lesión
    0.06
     tient
    0.05
    कर्ता
    0.05
     NE
    0.05
     T
    0.05
    Activations Density 0.002%

    No Known Activations