© 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. 129174
    Prev
    Next
    INDEX
    Explanations

    activities followed by prepositions

    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
     તેમણે
    -0.06
    ira
    -0.05
    -
    -0.05
    essayer
    -0.05
     necessariamente
    -0.05
     преимущественно
    -0.05
     nenhuma
    -0.05
     principalmente
    -0.05
    ura
    -0.05
     sejam
    -0.05
    POSITIVE LOGITS
     trés
    0.07
     sogar
    0.07
     activités
    0.07
    どころ
    0.07
    gevens
    0.07
     Both
    0.06
     activity
    0.06
     both
    0.06
     cuz
    0.06
    !!!
    0.06
    Activations Density 0.011%

    No Known Activations