© 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. 129468
    Prev
    Next
    INDEX
    Explanations

    code prefixes and names

    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
     உருவாக்கி
    -0.07
     التالية
    -0.07
     ود
    -0.06
     voh
    -0.06
    ciąż
    -0.06
     etab
    -0.06
     awkwardly
    -0.06
    சிக்க
    -0.06
    创建
    -0.06
    台風
    -0.06
    POSITIVE LOGITS
    gggg
    0.06
     feminine
    0.06
    lovely
    0.05
    ‡
    0.05
     sideboard
    0.05
     lorsque
    0.05
     good
    0.05
    닫
    0.05
    designs
    0.05
     chương
    0.05
    Activations Density 0.003%

    No Known Activations