© 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. 10-GEMMASCOPE-RES-131K
    7. 105144
    Prev
    Next
    INDEX
    Explanations

    average followed by a quantity

    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_10/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
     längere
    -1.95
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.84
    2
    -1.70
    -1.67
    会有
    -1.67
     erwähnten
    -1.67
     technischen
    -1.66
     usando
    -1.66
     zwanzig
    -1.66
     gröss
    -1.65
    POSITIVE LOGITS
     one
    1.98
     all
    1.79
    ؛
    1.74
    诶
    1.71
     potes
    1.61
     at
    1.60
    哟
    1.59
    𖡼
    1.54
    
    1.53
     an
    1.52
    Activations Density 0.020%
    No Known Activations