© 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. 33782
    Prev
    Next
    INDEX
    Explanations

    broadcast to everyone

    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
    ουργ
    -0.85
    glGen
    -0.84
     podczas
    -0.81
    InputData
    -0.79
    requests
    -0.78
     requests
    -0.77
    ี้ย
    -0.74
     入力
    -0.72
    getInput
    -0.72
    Suspicious
    -0.72
    POSITIVE LOGITS
     broadcast
    2.61
    broadcast
    2.41
     Broadcast
    2.19
     everyone
    2.17
    Broadcast
    2.06
     broadcasting
    2.02
     everybody
    1.95
    广播
    1.73
     broadcasts
    1.73
    everyone
    1.63
    Activations Density 0.019%

    No Known Activations