© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128868
    Prev
    Next
    INDEX
    Explanations

    programming output commands

    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
     desir
    -0.06
     его
    -0.06
     other
    -0.06
     anytime
    -0.06
     ادامه
    -0.06
     extol
    -0.06
    DisplayName
    -0.06
     हर
    -0.06
     בכל
    -0.06
     incomparable
    -0.06
    POSITIVE LOGITS
     lediglich
    0.07
     اکثریت
    0.06
     niektó
    0.06
    ැනි
    0.06
    টসম্যান
    0.06
     analogs
    0.06
    新型
    0.06
    几个
    0.06
    cooking
    0.06
     fatality
    0.06
    Activations Density 0.001%

    No Known Activations