© 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. 120705
    Prev
    Next
    INDEX
    Explanations

    r, R, Research, Review

    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
    Each
    -0.07
    Without
    -0.06
     प्रत्येक
    -0.06
    When
    -0.06
     Without
    -0.06
     סי
    -0.06
     incluyendo
    -0.06
     INCLUDING
    -0.06
     khi
    -0.06
     engraving
    -0.06
    POSITIVE LOGITS
     revival
    0.06
     largo
    0.06
     إعادة
    0.06
     Revival
    0.06
     resurrection
    0.06
    醒
    0.06
    居然
    0.06
     re
    0.06
     renewals
    0.06
    REX
    0.06
    Activations Density 0.026%

    No Known Activations