© 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. 118017
    Prev
    Next
    INDEX
    Explanations

    academic and proper nouns

    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
     stejně
    -0.07
     идеально
    -0.06
    Offer
    -0.06
     ერთ
    -0.06
     mungkin
    -0.06
    简约
    -0.06
     approvals
    -0.06
    成立于
    -0.06
     něco
    -0.06
     najlepiej
    -0.06
    POSITIVE LOGITS
     Cookbook
    0.06
     included
    0.06
     Mark
    0.06
     शांत
    0.06
     critic
    0.06
     massive
    0.05
     irritate
    0.05
    বির
    0.05
    砕
    0.05
    球队
    0.05
    Activations Density 0.001%

    No Known Activations