© 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. 103342
    Prev
    Next
    INDEX
    Explanations

    back, backup, and 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_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
     Như
    -0.85
     yayınları
    -0.81
    őle
    -0.81
     साथ
    -0.81
     Probable
    -0.81
    氵
    -0.79
     підприєм
    -0.78
    urri
    -0.78
     extremos
    -0.77
     <<"
    -0.76
    POSITIVE LOGITS
     spirited
    0.86
     Back
    0.82
     slogan
    0.73
     fully
    0.71
     золо
    0.70
    urities
    0.70
     appropriation
    0.69
    vok
    0.68
    scr
    0.67
     unver
    0.67
    Activations Density 0.039%

    No Known Activations