© 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. 129696
    Prev
    Next
    INDEX
    Explanations

    introductions and questions

    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
     presently
    -0.07
     сейчас
    -0.07
     بالق
    -0.07
     shouldn
    -0.07
     notwithstanding
    -0.06
    現在は
    -0.06
     currently
    -0.06
     지금
    -0.06
    েইল
    -0.06
     atraer
    -0.06
    POSITIVE LOGITS
    曾
    0.06
     duodenum
    0.06
     উদ্বে
    0.06
     klanten
    0.06
     ogen
    0.06
    massage
    0.05
     necesariamente
    0.05
    Used
    0.05
    代
    0.05
    ılım
    0.05
    Activations Density 0.004%

    No Known Activations