© 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. 90321
    Prev
    Next
    INDEX
    Explanations

    leading or ahead

    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
    ecan
    -0.77
    éle
    -0.76
    förm
    -0.76
     pierwszej
    -0.74
    dized
    -0.72
    ͦ
    -0.71
    ıdır
    -0.71
     ſen
    -0.70
     teratur
    -0.69
     Brande
    -0.69
    POSITIVE LOGITS
     leading
    4.25
     lead
    3.61
    Leading
    3.55
     Leading
    3.48
     leads
    3.45
    leading
    3.33
    lead
    2.80
     Leads
    2.75
    LEADING
    2.73
    Lead
    2.72
    Activations Density 0.039%

    No Known Activations