© 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. 129140
    Prev
    Next
    INDEX
    Explanations

    proper nouns followed by names

    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
     según
    -0.07
     documents
    -0.06
     allowable
    -0.06
     Selon
    -0.06
     IMPLIED
    -0.06
    indicated
    -0.06
    Selon
    -0.06
     recomendaciones
    -0.06
     selon
    -0.06
     بنت
    -0.06
    POSITIVE LOGITS
     我們
    0.06
    ்சை
    0.06
    repeat
    0.06
     reak
    0.06
    คือ
    0.06
    ..,
    0.06
     обычно
    0.06
     повто
    0.06
    ularity
    0.06
     повторя
    0.06
    Activations Density 0.001%

    No Known Activations