© 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. 130527
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols

    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
     지금
    -0.08
     dieser
    -0.07
    지금
    -0.07
     einige
    -0.07
     alguns
    -0.07
     약간
    -0.07
     هذه
    -0.06
     몇
    -0.06
     these
    -0.06
    எஸ்
    -0.06
    POSITIVE LOGITS
     
    0.06
     состоит
    0.06
     Powers
    0.06
    始める
    0.05
     fruct
    0.05
     joyful
    0.05
     delights
    0.05
     delightfully
    0.05
     joyous
    0.05
     consists
    0.05
    Activations Density 0.001%

    No Known Activations