© 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. 119650
    Prev
    Next
    INDEX
    Explanations

    content repackaged or original work

    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
     definitely
    -0.06
     переход
    -0.06
     specifically
    -0.06
    Ľ
    -0.06
     rząd
    -0.06
    跟随
    -0.06
    ércio
    -0.06
     abnormal
    -0.05
    Specifically
    -0.05
     coordinator
    -0.05
    POSITIVE LOGITS
     repack
    0.07
    derived
    0.07
     Derived
    0.06
    Derived
    0.06
    attributed
    0.06
     Quelle
    0.06
    credited
    0.06
     derivada
    0.06
    Vertical
    0.06
    Opportun
    0.06
    Activations Density 0.048%

    No Known Activations