© 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. 66029
    Prev
    Next
    INDEX
    Explanations

    drilling tools

    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
     hangat
    -0.77
     hook
    -0.72
    ื้น
    -0.71
    Toss
    -0.70
    Enrique
    -0.70
     Zwick
    -0.70
    上官
    -0.69
    unicorn
    -0.69
    前世
    -0.68
    hook
    -0.68
    POSITIVE LOGITS
     tool
    1.05
    tool
    0.97
     tools
    0.93
    Tool
    0.91
     Tool
    0.88
    工具
    0.88
     ابزار
    0.84
    RESS
    0.84
     TOOL
    0.84
     Hughes
    0.82
    Activations Density 0.096%

    No Known Activations