© 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. 92407
    Prev
    Next
    INDEX
    Explanations

    ending or over

    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
    🏟
    -0.80
    aglio
    -0.79
    воз
    -0.79
    了起来
    -0.75
     サッカー
    -0.74
     chaleco
    -0.73
    berte
    -0.71
    俱乐部
    -0.70
    wegs
    -0.70
    问题
    -0.70
    POSITIVE LOGITS
     over
    4.78
    over
    2.47
    Over
    2.23
     OVER
    2.22
     Over
    2.14
     över
    2.13
     над
    1.75
     sobre
    1.66
     vorbei
    1.63
    OVER
    1.62
    Activations Density 0.019%

    No Known Activations