© 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. 129304
    Prev
    Next
    INDEX
    Explanations

    GENERATED, Diminished, Microorganisms, Tip, xml

    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
    าร
    -0.07
    behind
    -0.06
     계산
    -0.06
     약간
    -0.06
    fasterxml
    -0.06
    maschinen
    -0.06
     choose
    -0.06
    قع
    -0.06
     klicken
    -0.06
     nasel
    -0.06
    POSITIVE LOGITS
     I
    0.06
    是
    0.06
     من
    0.06
     я
    0.06
     अधिकार
    0.06
    (['
    0.06
     पहली
    0.05
    是他
    0.05
     كان
    0.05
    中的
    0.05
    Activations Density 0.001%

    No Known Activations