© 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. 129098
    Prev
    Next
    INDEX
    Explanations

    advantageous, preferred, experimental, operating

    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
    without
    -0.06
     marrying
    -0.05
     indicating
    -0.05
    lying
    -0.05
    by
    -0.05
     বলেই
    -0.05
    更多
    -0.05
    indicating
    -0.05
     substantially
    -0.05
     without
    -0.05
    POSITIVE LOGITS
     cosidd
    0.07
     facilitation
    0.07
     для
    0.07
     якобы
    0.07
     sogenannten
    0.07
     أي
    0.06
     basicamente
    0.06
     kde
    0.06
     tidligere
    0.06
     básicamente
    0.06
    Activations Density 0.005%

    No Known Activations