© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118771
    Prev
    Next
    INDEX
    Explanations

    date context openers

    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
     with
    -0.07
     through
    -0.06
     با
    -0.06
     через
    -0.06
     потребо
    -0.06
     melalui
    -0.06
     auditor
    -0.06
     disrespect
    -0.06
    after
    -0.06
     μέσω
    -0.06
    POSITIVE LOGITS
    젊
    0.07
    除去
    0.06
    ifices
    0.06
     يمكنك
    0.06
    ത്തില്‍
    0.06
     waż
    0.06
     buona
    0.06
     ambi
    0.06
    重要
    0.06
    重要的
    0.06
    Activations Density 0.002%

    No Known Activations