© 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. 119730
    Prev
    Next
    INDEX
    Explanations

    year or date

    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
     riusc
    -0.06
    avion
    -0.06
     doing
    -0.06
     (!)
    -0.05
     Succeed
    -0.05
     result
    -0.05
     descendants
    -0.05
    鍛
    -0.05
    过来
    -0.05
    '
    -0.05
    POSITIVE LOGITS
     மேற்கொண்ட
    0.06
    其中
    0.06
     pretože
    0.06
    योग्य
    0.06
     एमसी
    0.06
     क्षमताओं
    0.06
    PCF
    0.06
    ೃಷ್ಟ
    0.06
     część
    0.06
     the
    0.06
    Activations Density 0.001%

    No Known Activations