© 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. 128362
    Prev
    Next
    INDEX
    Explanations

    electrical connectors and terminals

    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
     Easy
    -0.06
     when
    -0.06
    Easy
    -0.06
     표시
    -0.06
     offered
    -0.06
    Esta
    -0.06
     ofrece
    -0.06
    дяки
    -0.06
     EASY
    -0.06
     Parking
    -0.06
    POSITIVE LOGITS
     hereafter
    0.07
    更改
    0.06
    に変更
    0.06
    の原因
    0.06
     আয়
    0.06
    无比
    0.06
     elaboration
    0.05
     сега
    0.05
    inprogress
    0.05
     causality
    0.05
    Activations Density 0.029%

    No Known Activations