© 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. 119179
    Prev
    Next
    INDEX
    Explanations

    only, a, an, the, some, each, can

    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
     as
    -0.06
     strumenti
    -0.06
     provenienti
    -0.06
     elec
    -0.05
     Memorandum
    -0.05
    Luther
    -0.05
    ணிய
    -0.05
     ως
    -0.05
    শূন্য
    -0.05
    作為
    -0.05
    POSITIVE LOGITS
     only
    0.09
    可能是
    0.08
     možda
    0.08
     tylko
    0.08
    only
    0.07
    只有
    0.07
     probably
    0.07
     только
    0.07
    可能会
    0.07
     hanya
    0.07
    Activations Density 0.040%

    No Known Activations