© 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. 118787
    Prev
    Next
    INDEX
    Explanations

    numbers, common words, and symbols

    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
     отече
    -0.07
     stories
    -0.06
     articles
    -0.06
     also
    -0.06
    лни
    -0.06
     मजब
    -0.06
    ani
    -0.06
    ほどの
    -0.06
     разгово
    -0.05
    ŋ
    -0.05
    POSITIVE LOGITS
     terminée
    0.07
    uterine
    0.07
     Ghent
    0.06
    将会
    0.06
     উত্তরাধ
    0.06
    すれば
    0.06
    probs
    0.06
     quadratic
    0.06
     voici
    0.06
     exponential
    0.06
    Activations Density 0.003%

    No Known Activations