© 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. 76581
    Prev
    Next
    INDEX
    Explanations

    crowning achievement or bonus

    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
    }_{
    -0.87
     alcune
    -0.79
     Gegenstände
    -0.77
     وكذلك
    -0.76
    prav
    -0.75
    vědět
    -0.75
    佐々木
    -0.73
     OBL
    -0.73
    percentage
    -0.72
    不妨
    -0.72
    POSITIVE LOGITS
     icing
    4.84
     cherry
    4.66
    cherry
    3.48
    icing
    2.91
    Cherry
    2.86
     Cherry
    2.80
     frosting
    2.30
     cherries
    2.30
     kicker
    1.98
     crowning
    1.95
    Activations Density 0.020%

    No Known Activations