© 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. 117301
    Prev
    Next
    INDEX
    Explanations

    provided with

    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
     其
    -0.07
     ثم
    -0.06
    然後
    -0.06
    然后
    -0.06
     ይሰ
    -0.06
    იზ
    -0.06
    ೩
    -0.06
     presión
    -0.06
     tanto
    -0.06
    rut
    -0.06
    POSITIVE LOGITS
     between
    0.07
     giữa
    0.06
     zwischen
    0.06
     رغم
    0.06
     सबके
    0.06
    だけでも
    0.06
    才能
    0.05
    फ
    0.05
     was
    0.05
     শীর্ষে
    0.05
    Activations Density 0.011%

    No Known Activations