© 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. 116402
    Prev
    Next
    INDEX
    Explanations

    special characters and code structures

    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
     bronze
    -0.06
    беріга
    -0.06
     så
    -0.06
     காற்றின்
    -0.05
    似的
    -0.05
     உண்டு
    -0.05
     я
    -0.05
    cil
    -0.05
     flotte
    -0.05
    🦞
    -0.05
    POSITIVE LOGITS
    quickly
    0.07
     자신
    0.06
     모두
    0.06
     옮
    0.06
     সংলাপ
    0.06
     it
    0.06
     also
    0.06
    也将
    0.06
     ஆகியவை
    0.06
    Surprisingly
    0.06
    Activations Density 0.001%

    No Known Activations