© 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. 128641
    Prev
    Next
    INDEX
    Explanations

    grep commands

    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
     that
    -0.08
     type
    -0.07
     أن
    -0.06
    xygen
    -0.06
    Trước
    -0.06
     ज्वेल
    -0.06
    XYGEN
    -0.06
    솎
    -0.06
     TYPE
    -0.06
     heterosexual
    -0.06
    POSITIVE LOGITS
     hva
    0.06
     possibili
    0.06
    possible
    0.06
    各
    0.06
     possibile
    0.06
     intervals
    0.06
     Possible
    0.06
     gewährle
    0.06
     keinginan
    0.06
    🐀
    0.06
    Activations Density 0.001%

    No Known Activations