© 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. 116316
    Prev
    Next
    INDEX
    Explanations

    structures, constructions, export

    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
     depicts
    -0.07
    cuando
    -0.07
    appartement
    -0.06
     represents
    -0.06
     indique
    -0.06
     provides
    -0.06
    击
    -0.06
     changeable
    -0.06
     deği
    -0.06
     любят
    -0.06
    POSITIVE LOGITS
     Constructions
    0.07
     constructions
    0.06
     discriminated
    0.06
     Hasil
    0.06
     structures
    0.06
     structuring
    0.06
     سعی
    0.06
     middlemen
    0.06
     estructuras
    0.06
    ₹
    0.06
    Activations Density 0.051%

    No Known Activations