© 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. 128357
    Prev
    Next
    INDEX
    Explanations

    issued to 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
     durante
    -0.07
     during
    -0.06
     четыре
    -0.06
    期间
    -0.06
    期間
    -0.06
     आपसी
    -0.06
     four
    -0.06
    氇
    -0.06
     während
    -0.06
     facendo
    -0.06
    POSITIVE LOGITS
     있다면
    0.08
     if
    0.07
     If
    0.07
    といえば
    0.07
     badly
    0.06
     varsa
    0.06
     ruangan
    0.06
     ถ้า
    0.06
    如果是
    0.06
     い
    0.06
    Activations Density 0.002%

    No Known Activations