© 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. 118519
    Prev
    Next
    INDEX
    Explanations

    numbers and groups

    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
     differenza
    -0.06
     humain
    -0.06
     traditions
    -0.06
     tradiciones
    -0.06
     unlike
    -0.06
     humaine
    -0.06
     gewinnen
    -0.05
    mentioned
    -0.05
     mencionado
    -0.05
     modest
    -0.05
    POSITIVE LOGITS
    诋
    0.07
     Various
    0.06
     tuvimos
    0.06
     例えば
    0.06
    ocio
    0.06
     Aí
    0.06
    સ્પ
    0.06
    ić
    0.06
     tanıml
    0.06
    μορφ
    0.06
    Activations Density 0.030%

    No Known Activations