© 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. 118076
    Prev
    Next
    INDEX
    Explanations

    technical abbreviations and compounds

    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
     obwohl
    -0.06
     இறை
    -0.06
     ;)
    -0.06
     ;-)
    -0.06
     (~
    -0.06
     corroborated
    -0.06
     hehe
    -0.06
     istor
    -0.06
     :-)
    -0.06
     haha
    -0.06
    POSITIVE LOGITS
     gelecek
    0.06
     अतिक
    0.06
     rosto
    0.06
     principi
    0.06
     взаимо
    0.06
    helping
    0.06
     siento
    0.06
     موا
    0.06
     Sentence
    0.06
     Paragraph
    0.05
    Activations Density 0.005%

    No Known Activations