© 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. 117088
    Prev
    Next
    INDEX
    Explanations

    substrate or support material

    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
     valid
    -0.07
     specified
    -0.06
    eline
    -0.06
    相应
    -0.06
    incorpor
    -0.06
     defendants
    -0.06
    ട്
    -0.05
    アド
    -0.05
    ज्ञा
    -0.05
     Maximal
    -0.05
    POSITIVE LOGITS
    Instead
    0.07
     가진
    0.07
     enterprising
    0.07
    instead
    0.06
     maiores
    0.06
     Bengals
    0.06
     kaufen
    0.06
     miał
    0.06
    蜮
    0.06
     त्यांची
    0.06
    Activations Density 0.008%

    No Known Activations