© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57353
    Prev
    Next
    INDEX
    Explanations

    agents and change

    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
    siella
    -0.82
    Between
    -0.80
    vised
    -0.79
    지는
    -0.77
    uit
    -0.74
    ts
    -0.74
    db
    -0.73
     weekdays
    -0.73
    son
    -0.71
    uid
    -0.71
    POSITIVE LOGITS
     agent
    1.58
     agents
    1.41
     Agents
    1.32
     Agent
    1.30
    agent
    1.30
    AGENT
    1.27
     AGENT
    1.23
    Agent
    1.20
    Agents
    1.20
     agente
    1.18
    Activations Density 0.014%

    No Known Activations