© 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. 12093
    Prev
    Next
    INDEX
    Explanations

    minimal degree or absence

    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
    xvii
    -3.03
     アート
    -2.94
    xix
    -2.89
    
    -2.84
     Spanyol
    -2.72
    GEBUR
    -2.67
     capace
    -2.66
    
    -2.66
    mbgg
    -2.64
     แต่
    -2.63
    POSITIVE LOGITS
    C
    3.52
    You
    3.19
    Following
    3.08
    While
    2.98
    1
    2.98
    What
    2.91
    This
    2.89
    Using
    2.88
    With
    2.86
    蛧
    2.84
    Activations Density 0.005%

    No Known Activations