© 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. 130865
    Prev
    Next
    INDEX
    Explanations

    time and era

    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
    psi
    -0.06
     деше
    -0.06
     gejala
    -0.05
    antics
    -0.05
    霝
    -0.05
     correlate
    -0.05
    里面的
    -0.05
     கண்டுபி
    -0.05
     ఫి
    -0.05
     epist
    -0.05
    POSITIVE LOGITS
     একটু
    0.06
     конкре
    0.06
     Started
    0.06
    INDUST
    0.06
    ওয়
    0.06
     fresh
    0.06
     whitespace
    0.06
     हस्त
    0.06
    いわ
    0.06
    TNT
    0.06
    Activations Density 0.010%

    No Known Activations