© 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. 129933
    Prev
    Next
    INDEX
    Explanations

    data types and scientific concepts

    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
    जिकल
    -0.07
     شاید
    -0.06
     संस्कार
    -0.06
     навіть
    -0.06
     probabilmente
    -0.06
     posiblemente
    -0.06
     giveaway
    -0.06
     probablemente
    -0.06
     probablement
    -0.06
     رنگ
    -0.06
    POSITIVE LOGITS
     method
    0.07
     condensation
    0.06
    IMPLEMENT
    0.06
     Pompe
    0.06
     they
    0.06
     কোনটা
    0.06
     careful
    0.06
     judicious
    0.05
    method
    0.05
    jahr
    0.05
    Activations Density 0.003%

    No Known Activations