© 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. 128858
    Prev
    Next
    INDEX
    Explanations

    video game consoles and systems

    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
     unlimited
    -0.07
    locally
    -0.07
     विचित्र
    -0.06
    itley
    -0.06
     получать
    -0.06
    glfw
    -0.06
     现在
    -0.06
    ได้รับ
    -0.06
     berapa
    -0.06
     abrir
    -0.06
    POSITIVE LOGITS
    :
    0.07
    rival
    0.06
     data
    0.06
     følgende
    0.05
    /
    0.05
    собенно
    0.05
    OMBRE
    0.05
     following
    0.05
    Songs
    0.05
     or
    0.05
    Activations Density 0.006%

    No Known Activations