© 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. 119282
    Prev
    Next
    INDEX
    Explanations

    html formatting and transformations

    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
     Nazi
    -0.06
    এমন
    -0.06
    าระ
    -0.06
    !!!"
    -0.06
    ("__
    -0.06
     huge
    -0.06
     belieb
    -0.06
    pickle
    -0.06
    অম
    -0.06
     usually
    -0.06
    POSITIVE LOGITS
     transformation
    0.07
     параметров
    0.07
    用到
    0.07
     transforming
    0.07
     transformations
    0.07
    granted
    0.06
    Transformation
    0.06
     transformación
    0.06
    变换
    0.06
    applied
    0.06
    Activations Density 0.003%

    No Known Activations