© 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. 118004
    Prev
    Next
    INDEX
    Explanations

    entirely, completely, fully

    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
     thúc
    -0.07
     favourable
    -0.06
    圖像
    -0.06
    Dios
    -0.06
     unlike
    -0.06
     favoured
    -0.06
    getTarget
    -0.06
     okam
    -0.06
     units
    -0.06
    好評
    -0.06
    POSITIVE LOGITS
     completo
    0.07
    nyi
    0.07
     completa
    0.07
    完整的
    0.07
    全部
    0.07
     entire
    0.07
     complete
    0.07
     كامل
    0.07
     полностью
    0.06
     যাবত
    0.06
    Activations Density 0.085%

    No Known Activations