© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64486
    Prev
    Next
    INDEX
    Explanations

    spy, agent, operatives, secret, undercover

    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
     ERK
    -0.80
     alcalde
    -0.80
    मति
    -0.79
     AHL
    -0.79
    驛
    -0.79
     cozin
    -0.79
    Helmet
    -0.79
    塹
    -0.78
    Police
    -0.77
     Kategor
    -0.77
    POSITIVE LOGITS
     agent
    2.80
     agents
    2.77
     Agent
    2.56
    Agent
    2.45
    Agents
    2.42
     Agents
    2.34
    agents
    2.31
    agent
    2.27
     operatives
    2.08
     AGENT
    1.95
    Activations Density 0.089%

    No Known Activations