© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116174
    Prev
    Next
    INDEX
    Explanations

    end of code blocks

    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
     if
    -0.07
    extra
    -0.07
    if
    -0.06
     njen
    -0.05
     retrouve
    -0.05
     nay
    -0.05
    are
    -0.05
    仲間
    -0.05
    ...............
    -0.05
     இன்னொரு
    -0.05
    POSITIVE LOGITS
     establecimiento
    0.07
     математи
    0.07
    hetical
    0.07
     विशिष्ट
    0.07
     những
    0.06
     một
    0.06
     became
    0.06
     aromat
    0.06
    私たち
    0.06
    owsky
    0.06
    Activations Density 0.003%

    No Known Activations