© 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. 117848
    Prev
    Next
    INDEX
    Explanations

    length of intervals

    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
     ഏറെ
    -0.07
    婉
    -0.06
     ẩn
    -0.06
    ANY
    -0.06
    下方
    -0.06
     শুধু
    -0.06
    কল্যা
    -0.06
     कहते
    -0.06
    かなり
    -0.06
     rarest
    -0.06
    POSITIVE LOGITS
     correct
    0.08
     sufficient
    0.07
     appropriate
    0.06
     suitable
    0.06
     требованиям
    0.06
     ಈಗಾಗಲೇ
    0.06
     म्हणून
    0.06
     subsections
    0.06
     safely
    0.06
    ithin
    0.06
    Activations Density 0.027%

    No Known Activations