© 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. 109631
    Prev
    Next
    INDEX
    Explanations

    agent, agents

    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
     Eingang
    -1.19
    屣
    -0.96
     interessi
    -0.95
     gebouw
    -0.95
    噘
    -0.94
    Copia
    -0.94
     enthusiast
    -0.93
     glorified
    -0.91
    Contexto
    -0.91
    ónimos
    -0.90
    POSITIVE LOGITS
     Agent
    2.03
     agent
    2.00
    Agent
    1.86
     Agents
    1.86
     provoc
    1.84
    agent
    1.77
     agents
    1.53
    Agents
    1.48
     agentes
    1.42
     AGENT
    1.42
    Activations Density 0.017%

    No Known Activations