© 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. 85178
    Prev
    Next
    INDEX
    Explanations

    introduction

    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
     this
    -2.33
     showed
    -1.81
     to
    -1.81
     D
    -1.78
     helps
    -1.77
     Makes
    -1.77
     U
    -1.70
     keeps
    -1.66
     had
    -1.66
     serves
    -1.66
    POSITIVE LOGITS
     rése
    1.86
    ꔹ
    1.84
    粜
    1.82
     florales
    1.77
     étan
    1.76
    禟
    1.76
    觊
    1.73
     SPECIAL
    1.71
     花朵
    1.70
     ſie
    1.68
    Activations Density 0.016%

    No Known Activations