© 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. 119106
    Prev
    Next
    INDEX
    Explanations

    home or away games

    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
    合理的
    -0.07
    咁
    -0.07
    内的
    -0.06
    profile
    -0.06
    itational
    -0.06
     संतुलित
    -0.06
     가능한
    -0.06
    天才
    -0.06
     될
    -0.06
     profile
    -0.06
    POSITIVE LOGITS
    Corresponding
    0.06
     Entscheidung
    0.06
    在这里
    0.06
     समिती
    0.05
     louder
    0.05
     loudest
    0.05
    :*
    0.05
    实例化
    0.05
    鸰
    0.05
    createNew
    0.05
    Activations Density 0.005%

    No Known Activations