© 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. 118956
    Prev
    Next
    INDEX
    Explanations

    Characterization, encrustation, use

    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
     procedure
    -0.06
     máy
    -0.06
    Volunteer
    -0.06
     купить
    -0.06
     rules
    -0.06
     সত্ত্বেও
    -0.06
    一件
    -0.06
    ຊ
    -0.06
    ång
    -0.06
     machine
    -0.06
    POSITIVE LOGITS
     empie
    0.07
    ;,
    0.07
    ;;
    0.06
    idemargin
    0.06
    Wenn
    0.06
     contemporary
    0.06
     solamente
    0.06
    essive
    0.06
    ;-
    0.06
     glamorous
    0.06
    Activations Density 0.002%

    No Known Activations