© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103282
    Prev
    Next
    INDEX
    Explanations

    frustration or surprise exclamations

    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
     laughable
    -0.81
    geladen
    -0.80
    嘿嘿
    -0.79
     laug
    -0.79
    Iacute
    -0.76
     紀
    -0.73
     Cull
    -0.73
    病情
    -0.73
    铟
    -0.71
     chen
    -0.71
    POSITIVE LOGITS
     damn
    3.50
     darn
    3.00
     Damn
    3.00
    Damn
    2.75
     dammit
    2.63
     dang
    2.58
    damn
    2.58
     dam
    2.53
    dam
    2.42
     Darn
    2.23
    Activations Density 0.054%

    No Known Activations