© 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. 130890
    Prev
    Next
    INDEX
    Explanations

    stack, top, Zimbabwe Cricket, Devices, Chavez

    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
    Depth
    -0.06
     exclusivamente
    -0.06
     বর্ত
    -0.06
    ildren
    -0.06
    窮
    -0.06
     rừng
    -0.06
     स्तर
    -0.06
     niveau
    -0.06
    ระดับ
    -0.06
     Nested
    -0.06
    POSITIVE LOGITS
     VALID
    0.07
     anatom
    0.07
     ligeramente
    0.06
     encontrados
    0.06
     seeking
    0.06
    ";//
    0.06
     किरायेदारों
    0.06
     awk
    0.06
     légèrement
    0.06
    anatom
    0.05
    Activations Density 0.001%

    No Known Activations