© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 38337
    Prev
    Next
    INDEX
    Explanations

    Background

    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
     motivasi
    -0.90
    Гц
    -0.86
     Fakult
    -0.84
    щал
    -0.84
     cepat
    -0.81
     bzw
    -0.81
    Dzi
    -0.79
    ХА
    -0.79
     toppen
    -0.79
    ülle
    -0.79
    POSITIVE LOGITS
     irgendwann
    0.84
     speaker
    0.81
     gewüns
    0.80
     Welcome
    0.79
    ウェル
    0.78
     podcast
    0.77
     welcome
    0.76
     umgeben
    0.76
    ブー
    0.75
     tâm
    0.74
    Activations Density 0.003%

    No Known Activations