© 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. 129607
    Prev
    Next
    INDEX
    Explanations

    program code keywords

    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
     সম্পর্
    -0.07
     contienen
    -0.07
     newborn
    -0.06
     milhares
    -0.06
     cientos
    -0.06
    НЕ
    -0.06
     styrene
    -0.06
    发行
    -0.06
    Normdaten
    -0.06
     carpenters
    -0.06
    POSITIVE LOGITS
    体育
    0.06
     commitments
    0.06
    することも
    0.05
     Power
    0.05
     sov
    0.05
    心
    0.05
    hog
    0.05
     probably
    0.05
     spac
    0.05
     дороги
    0.05
    Activations Density 0.002%

    No Known Activations