© 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. 118580
    Prev
    Next
    INDEX
    Explanations

    new or subsequent actions

    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
    BackgroundImage
    -0.06
    اول
    -0.06
     pertama
    -0.06
     kucing
    -0.06
    的他
    -0.06
     Faites
    -0.06
     eerste
    -0.06
     दोन
    -0.05
    नों
    -0.05
     два
    -0.05
    POSITIVE LOGITS
     নতুন
    0.07
     nuove
    0.07
     புதிய
    0.07
     새로운
    0.06
    নতুন
    0.06
     surging
    0.06
     new
    0.06
     новое
    0.06
     nuevas
    0.06
    itional
    0.06
    Activations Density 0.039%

    No Known Activations