© 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. 118701
    Prev
    Next
    INDEX
    Explanations

    numbers, code, or specific locations

    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
     video
    -0.06
    video
    -0.06
     Audio
    -0.06
     became
    -0.06
    osphere
    -0.06
     Negro
    -0.06
     giám
    -0.05
    เสมอ
    -0.05
    Video
    -0.05
    στη
    -0.05
    POSITIVE LOGITS
    igere
    0.07
     poden
    0.06
    選挙
    0.06
    ៩
    0.06
     literalmente
    0.06
     yath
    0.06
     elecciones
    0.06
    Literal
    0.06
     純正
    0.06
    harusnya
    0.06
    Activations Density 0.003%

    No Known Activations