© 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. 116926
    Prev
    Next
    INDEX
    Explanations

    not a function

    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
    Unser
    -0.06
     với
    -0.06
     dengan
    -0.06
    តែ
    -0.05
     Ney
    -0.05
     στην
    -0.05
     নেতৃত্বের
    -0.05
    떼
    -0.05
     জাহ
    -0.05
     lis
    -0.05
    POSITIVE LOGITS
     correspond
    0.08
    corresponding
    0.08
     corresponds
    0.08
     corresponding
    0.07
     corrispond
    0.06
    也都
    0.06
     geek
    0.06
     yardımcı
    0.06
    Refresh
    0.06
    走行
    0.06
    Activations Density 0.003%

    No Known Activations