© 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. 118704
    Prev
    Next
    INDEX
    Explanations

    delivery services

    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
    ото
    -0.06
    েরই
    -0.06
     خراب
    -0.06
    =='
    -0.06
     belonging
    -0.06
     utilisés
    -0.06
    లపై
    -0.06
     वापरा
    -0.06
     belongs
    -0.06
    ()'
    -0.06
    POSITIVE LOGITS
     subsidies
    0.07
     communiquer
    0.06
     contactless
    0.06
     през
    0.06
     selam
    0.06
     EFFECT
    0.06
     DROP
    0.06
     अकाउंट
    0.06
    มอบ
    0.06
     communicated
    0.06
    Activations Density 0.040%

    No Known Activations