© 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. 130912
    Prev
    Next
    INDEX
    Explanations

    exit keys and actions

    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
     if
    -0.06
    ffiti
    -0.06
     comunicación
    -0.06
     ভ্রম
    -0.06
    本格
    -0.06
    iseksi
    -0.06
    正如
    -0.06
    Jeśli
    -0.06
     prep
    -0.06
     different
    -0.06
    POSITIVE LOGITS
    responseData
    0.06
    GRANT
    0.06
     बचने
    0.06
     cytometry
    0.06
     등이
    0.06
    ità
    0.05
    ёв
    0.05
     Pressed
    0.05
     osmosis
    0.05
    <0xA1>
    0.05
    Activations Density 0.001%

    No Known Activations