© 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. 120329
    Prev
    Next
    INDEX
    Explanations

    copyright notices and headers

    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
     that
    -0.06
    ᒍ
    -0.06
     we
    -0.06
     внима
    -0.06
     সেজন্য
    -0.06
     all
    -0.06
     о
    -0.05
    о
    -0.05
    О
    -0.05
    А
    -0.05
    POSITIVE LOGITS
    дт
    0.06
    *,
    0.06
     exert
    0.06
     elimina
    0.06
    StartX
    0.06
     elimination
    0.06
    并不是
    0.06
    픔
    0.06
     nicht
    0.06
     escritos
    0.06
    Activations Density 0.001%

    No Known Activations