© 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. 118293
    Prev
    Next
    INDEX
    Explanations

    arrival at locations

    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
     go
    -0.05
    oy
    -0.05
     early
    -0.05
     heralded
    -0.05
     بدء
    -0.05
     সংগ্রহের
    -0.05
     подтвер
    -0.05
     all
    -0.05
     aw
    -0.05
    開始
    -0.05
    POSITIVE LOGITS
    尽可能
    0.08
     максимально
    0.08
    かなり
    0.07
    諫
    0.07
    每个
    0.07
     эту
    0.07
     এই
    0.07
     هذه
    0.07
     இந்த
    0.07
    これを
    0.07
    Activations Density 0.013%

    No Known Activations