© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 117206
    Prev
    Next
    INDEX
    Explanations

    names followed by titles or descriptors

    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
    分为
    -0.07
     വിവിധ
    -0.07
    分為
    -0.07
     for
    -0.06
     раз
    -0.06
     впоследствии
    -0.06
     trasform
    -0.06
     গড়ে
    -0.06
     syg
    -0.06
     জন্য
    -0.06
    POSITIVE LOGITS
     entier
    0.07
    解决了
    0.06
    睡
    0.06
     sufferings
    0.06
     interrupting
    0.06
     doubly
    0.06
    しかった
    0.06
    အစိတ်အပိုင်း
    0.06
    ,
    0.06
     上
    0.06
    Activations Density 0.002%

    No Known Activations