© 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. 130656
    Prev
    Next
    INDEX
    Explanations

    copyright headers

    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
     phức
    -0.07
     sogar
    -0.07
    🚻
    -0.06
     Qf
    -0.06
     Даже
    -0.06
     великолеп
    -0.06
    Complex
    -0.06
     longed
    -0.06
    わず
    -0.06
     penit
    -0.06
    POSITIVE LOGITS
    他に
    0.06
     lainnya
    0.06
    inspir
    0.06
     prevenção
    0.05
     advantage
    0.05
     النت
    0.05
     گذشته
    0.05
     rehabilitation
    0.05
    其他
    0.05
     revival
    0.05
    Activations Density 0.007%

    No Known Activations