© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119238
    Prev
    Next
    INDEX
    Explanations

    mathematical text formatting

    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
     ваших
    -0.07
     a
    -0.07
     your
    -0.07
    에는
    -0.07
     the
    -0.06
     sooo
    -0.06
     medical
    -0.06
    称为
    -0.06
     Hoop
    -0.06
     प्रशास
    -0.06
    POSITIVE LOGITS
     när
    0.06
    bathy
    0.06
     MODELS
    0.05
    tainable
    0.05
    Contents
    0.05
    ⒋
    0.05
     recreated
    0.05
     একইভাবে
    0.05
    ceo
    0.05
    💧
    0.05
    Activations Density 0.001%

    No Known Activations