© 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. 10-GEMMASCOPE-RES-131K
    7. 11942
    Prev
    Next
    INDEX
    Explanations

    Taking the Lead

    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_10/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
    ers
    -1.84
     in
    -1.77
     it
    -1.74
     are
    -1.64
     by
    -1.61
    譬
    -1.60
    反思
    -1.59
     defines
    -1.57
     considérée
    -1.55
     knows
    -1.52
    POSITIVE LOGITS
    <bos>
    1.84
    ilets
    1.70
    
    1.66
    軚
    1.61
    ρους
    1.59
    rierten
    1.58
     بهداشتی
    1.54
    asties
    1.53
     rire
    1.51
    5
    1.49
    Activations Density 0.015%

    No Known Activations