© 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. 118103
    Prev
    Next
    INDEX
    Explanations

    | information

    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
     लगाते
    -0.07
     feminino
    -0.06
    Easy
    -0.06
    inių
    -0.06
     prisons
    -0.06
     Easy
    -0.06
    溧
    -0.06
     هغه
    -0.06
     EASY
    -0.06
     furniture
    -0.06
    POSITIVE LOGITS
    大神
    0.06
     보험
    0.06
    山
    0.06
     много
    0.06
     ה
    0.06
     ಒಂದ
    0.05
    意味
    0.05
    稱
    0.05
     ре
    0.05
    崖
    0.05
    Activations Density 0.003%

    No Known Activations