© 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. 117057
    Prev
    Next
    INDEX
    Explanations

    scientific paper titles

    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
     विवाह
    -0.07
     преимущества
    -0.06
     існу
    -0.06
     هناك
    -0.06
     alguns
    -0.06
     काही
    -0.06
     tốt
    -0.06
    ㅛ
    -0.06
     показывает
    -0.06
    ಗಳಿಗೆ
    -0.06
    POSITIVE LOGITS
    ambiente
    0.06
    charg
    0.06
    ftest
    0.05
    Searching
    0.05
    Repl
    0.05
    SEARCH
    0.05
     Dat
    0.05
     again
    0.05
     Finding
    0.05
    etted
    0.05
    Activations Density 0.002%

    No Known Activations