© 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. 116674
    Prev
    Next
    INDEX
    Explanations

    limiting quantity or results

    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
     any
    -0.06
    barui
    -0.06
     quaisquer
    -0.06
    ℂ
    -0.06
    ຖືກ
    -0.06
     പൊതു
    -0.06
     окре
    -0.05
     woodpe
    -0.05
    pflege
    -0.05
     cuyas
    -0.05
    POSITIVE LOGITS
     request
    0.07
     numeric
    0.06
     telescopic
    0.06
     maximum
    0.06
    請
    0.06
     Komb
    0.06
    paginate
    0.06
    Seit
    0.06
     query
    0.06
     limiting
    0.06
    Activations Density 0.016%

    No Known Activations