© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 129938
    Prev
    Next
    INDEX
    Explanations

    city now in

    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
     objectives
    -0.06
     suivants
    -0.06
     economies
    -0.06
     objectifs
    -0.05
     municipalities
    -0.05
     such
    -0.05
     keltiradi
    -0.05
     objetivos
    -0.05
     deliverables
    -0.05
     पूछता
    -0.05
    POSITIVE LOGITS
     বর্তমানে
    0.06
    一般的な
    0.06
     ۵
    0.06
     وقتی
    0.06
    dyž
    0.06
     সাধারণভাবে
    0.06
     кеңсесинде
    0.06
    默认
    0.06
     wajah
    0.06
     víctima
    0.06
    Activations Density 0.020%

    No Known Activations