© 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. 84194
    Prev
    Next
    INDEX
    Explanations

    objects interacting when dragged

    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
    Killed
    -0.94
     bescher
    -0.89
    planned
    -0.85
    Disconnected
    -0.82
     Lanes
    -0.82
    Planned
    -0.81
     mété
    -0.80
    gien
    -0.80
    ZIONE
    -0.78
     organisiert
    -0.77
    POSITIVE LOGITS
     interact
    2.05
     interaction
    1.95
     interacted
    1.76
     interacting
    1.74
    interact
    1.63
     Interaction
    1.55
     interactions
    1.53
    Interaction
    1.50
    interaction
    1.48
     interac
    1.47
    Activations Density 0.014%

    No Known Activations