© 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. 33743
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
     Nine
    -0.81
    九
    -0.81
    ９
    -0.77
    7
    -0.75
    ⁷
    -0.73
     "../../../
    -0.72
    URRED
    -0.71
     сем
    -0.71
    ás
    -0.71
    ПК
    -0.71
    POSITIVE LOGITS
    8
    1.09
     вось
    1.02
    3
    0.96
     eight
    0.93
     Eight
    0.79
    ৮
    0.79
    didReceive
    0.78
     Eighth
    0.76
    三個
    0.75
    ۸
    0.75
    Activations Density 0.058%

    No Known Activations