© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60822
    Prev
    Next
    INDEX
    Explanations

    Mario Bros

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     те
    -0.79
    娘娘
    -0.73
    gie
    -0.71
    いますが
    -0.70
    hf
    -0.70
     Gym
    -0.70
     Lancaster
    -0.70
    所有人
    -0.68
    izar
    -0.68
    甾
    -0.68
    POSITIVE LOGITS
     Bros
    1.37
    Bros
    1.05
     BROS
    1.02
     frères
    0.94
     bros
    0.91
    ￬
    0.90
     Brothers
    0.89
    bros
    0.88
    越高
    0.85
    joda
    0.85
    Activations Density 0.016%

    No Known Activations