© 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. 116909
    Prev
    Next
    INDEX
    Explanations

    without, not, never

    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
    ार्ज
    -0.07
     их
    -0.07
     ඔවුන්
    -0.06
     منهم
    -0.06
     खासकर
    -0.06
     nimi
    -0.06
    whether
    -0.06
    んですよね
    -0.06
     їх
    -0.06
     mereka
    -0.06
    POSITIVE LOGITS
     only
    0.08
     somente
    0.08
     فقط
    0.07
     ainult
    0.07
     только
    0.07
     tylko
    0.07
     chỉ
    0.07
     csak
    0.07
     puzzling
    0.06
     Only
    0.06
    Activations Density 0.071%

    No Known Activations