© 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. 128909
    Prev
    Next
    INDEX
    Explanations

    reported drastically

    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
     sheets
    -0.06
     تكون
    -0.06
    दृश्य
    -0.06
     सेवानिव
    -0.06
     تصير
    -0.06
     भोजपुरी
    -0.06
     tête
    -0.06
    strawberry
    -0.06
    PropertySheets
    -0.06
     sweeps
    -0.06
    POSITIVE LOGITS
     অবিশ্বাস্য
    0.07
     drastically
    0.07
     dramatically
    0.07
     reported
    0.07
     Reported
    0.07
     virkelig
    0.06
     materials
    0.06
     demonstrated
    0.06
     ingenious
    0.06
     unbelievable
    0.06
    Activations Density 0.004%

    No Known Activations