© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129903
    Prev
    Next
    INDEX
    Explanations

    denied

    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
    «,
    -0.06
     én
    -0.06
    ĵo
    -0.06
     Rxh
    -0.06
    ර්ථ
    -0.06
    Aggregation
    -0.06
    gebied
    -0.06
     triste
    -0.06
     gegeven
    -0.05
     средней
    -0.05
    POSITIVE LOGITS
     એટ
    0.06
    保证
    0.06
    ซี
    0.06
     into
    0.05
     This
    0.05
     kutoka
    0.05
     its
    0.05
     [
    0.05
     if
    0.05
     assuring
    0.05
    Activations Density 0.002%

    No Known Activations