© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130824
    Prev
    Next
    INDEX
    Explanations

    lecture or talk

    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
     razem
    -0.07
     organizar
    -0.07
     сотрудни
    -0.06
     rearing
    -0.06
     together
    -0.06
     nanotechnology
    -0.06
     frantically
    -0.06
     uproar
    -0.06
     együtt
    -0.06
    ছোট
    -0.06
    POSITIVE LOGITS
     vždy
    0.06
    View
    0.06
     either
    0.06
     easy
    0.05
     other
    0.05
     Lecture
    0.05
     wybr
    0.05
    MARK
    0.05
     ক্ষমতার
    0.05
     View
    0.05
    Activations Density 0.014%

    No Known Activations