© 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. 129918
    Prev
    Next
    INDEX
    Explanations

    library names and prefixes

    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
     Assembly
    -0.06
     ಹಾಗೂ
    -0.06
     পার্
    -0.06
     জাদু
    -0.05
     assembly
    -0.05
    Λ
    -0.05
     ب
    -0.05
    जूद
    -0.05
     prawidł
    -0.05
     perfectamente
    -0.05
    POSITIVE LOGITS
     when
    0.07
     হলেও
    0.06
    じゃない
    0.06
    験
    0.06
     पिछले
    0.06
    另一种
    0.06
    外国
    0.06
    Enfin
    0.06
     When
    0.06
     сен
    0.06
    Activations Density 0.008%

    No Known Activations