© 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. 103124
    Prev
    Next
    INDEX
    Explanations

    trigger events

    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
    keyframes
    -0.81
    valla
    -0.75
    onghi
    -0.73
    idom
    -0.71
    prop
    -0.71
     Roskov
    -0.71
    enoch
    -0.71
     Kear
    -0.71
    Hey
    -0.70
    dő
    -0.70
    POSITIVE LOGITS
     trigger
    1.30
     triggers
    1.13
     firing
    1.09
    triggers
    0.98
     Trigger
    0.95
    trigger
    0.95
     fired
    0.94
    triggered
    0.94
     decisión
    0.89
     coincidence
    0.89
    Activations Density 0.008%

    No Known Activations