© 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. 118979
    Prev
    Next
    INDEX
    Explanations

    number, 1, St, Introduction, 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
    purpose
    -0.06
     blí
    -0.06
     squadre
    -0.06
     박
    -0.06
    тувати
    -0.06
    ProjectType
    -0.06
    Jährige
    -0.06
    directly
    -0.06
    Roaming
    -0.06
     rápida
    -0.06
    POSITIVE LOGITS
     holde
    0.06
     नैतिक
    0.06
     sym
    0.06
    Urs
    0.05
     externes
    0.05
    gea
    0.05
     consolidating
    0.05
    ogra
    0.05
     ডাউন
    0.05
     этом
    0.05
    Activations Density 0.009%

    No Known Activations