© 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. 87132
    Prev
    Next
    INDEX
    Explanations

    only once or one instance

    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
    
    -0.85
     cuarenta
    -0.83
    又有
    -0.79
     treinta
    -0.77
    inafter
    -0.76
    豉
    -0.75
     هنگام
    -0.73
    ुट
    -0.73
    したのが
    -0.73
    atoria
    -0.72
    POSITIVE LOGITS
     once
    9.13
    once
    6.88
    Once
    6.72
     Once
    6.03
     ONCE
    5.63
     einmal
    5.34
    ONCE
    5.22
    一次
    4.41
    一度
    4.38
     egyszer
    4.06
    Activations Density 0.331%

    No Known Activations