© 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. 118224
    Prev
    Next
    INDEX
    Explanations

    class, type, or number

    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
     damal
    -0.08
     Dynamical
    -0.07
     gorgeous
    -0.07
     তখনকার
    -0.06
     Unterschied
    -0.06
     beautiful
    -0.06
     тогда
    -0.06
     damals
    -0.06
     मुसलमान
    -0.06
    үүл
    -0.06
    POSITIVE LOGITS
     coworkers
    0.07
     কখনোই
    0.07
    运行时
    0.06
     productivity
    0.06
     女
    0.06
     可以
    0.06
    োরে
    0.06
    ウエスト
    0.06
     statist
    0.06
    。(
    0.05
    Activations Density 0.123%

    No Known Activations