© 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. 38054
    Prev
    Next
    INDEX
    Explanations

    Introductions and chapters

    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
    ↵↵↵↵↵↵↵↵↵↵↵
    -1.09
    ↵↵↵↵↵↵
    -1.09
    ↵↵
    -1.08
    ↵↵↵↵↵
    -1.07
    ↵↵↵↵↵↵↵↵↵↵↵↵
    -1.05
    <blockquote>
    -1.02
    ↵↵↵↵↵↵↵↵↵↵
    -0.99
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.99
    ↵↵↵
    -0.98
    <h3>
    -0.98
    POSITIVE LOGITS
     Thoughts
    0.92
    ertale
    0.90
    useful
    0.89
    𝗅
    0.89
    tagged
    0.88
    Chapters
    0.88
     Introduction
    0.86
    țele
    0.84
    Rozm
    0.84
     Keluarga
    0.84
    Activations Density 0.023%

    No Known Activations