© 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. 109448
    Prev
    Next
    INDEX
    Explanations

    sound words like boom

    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
    轰隆隆
    -1.47
    轰隆
    -1.41
    咣
    -1.08
    嘁
    -1.01
    哐
    -0.96
    咔嚓
    -0.92
    簌
    -0.88
    嗖
    -0.84
    mic
    -0.74
    cout
    -0.74
    POSITIVE LOGITS
     boom
    2.48
     bang
    2.33
    boom
    2.06
     Boom
    2.05
    Boom
    1.93
     BOOM
    1.91
     thud
    1.88
     BANG
    1.80
    Bang
    1.77
    BOOM
    1.77
    Activations Density 0.023%

    No Known Activations