© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120843
    Prev
    Next
    INDEX
    Explanations

    police searching vehicles

    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
    Negative Logits
    发现
    -0.07
    發現
    -0.07
     обнару
    -0.06
     discovered
    -0.06
     результа
    -0.06
     clandest
    -0.06
     various
    -0.06
    結果
    -0.06
    طبيق
    -0.06
     serendip
    -0.06
    POSITIVE LOGITS
     jeżeli
    0.07
     waited
    0.06
     jeśli
    0.06
     अगर
    0.06
     consideración
    0.06
     expectativa
    0.06
     Makarna
    0.06
     intends
    0.06
    ಂತಹ
    0.06
     stoj
    0.06
    Activations Density 0.001%

    No Known Activations