© 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. 48120
    Prev
    Next
    INDEX
    Explanations

    tool or 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
    strzy
    -0.93
     Shooter
    -0.90
    owana
    -0.90
    خوا
    -0.90
     别墅
    -0.88
    inis
    -0.87
     waarbij
    -0.84
    ający
    -0.84
    ados
    -0.82
     caractéristique
    -0.82
    POSITIVE LOGITS
     tools
    3.30
     tool
    2.59
     Tools
    2.47
     toolbox
    2.33
    tools
    2.30
     arsenal
    2.13
    Tools
    2.06
    工具
    2.03
     available
    1.95
     toolkit
    1.95
    Activations Density 0.033%

    No Known Activations