© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68054
    Prev
    Next
    INDEX
    Explanations

    metacognition, in silico, Copyright, Cleanup

    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
    蓠
    -2.41
     unbelievably
    -1.98
     renowned
    -1.95
    撵
    -1.84
    細かく
    -1.84
     มัน
    -1.84
    秝
    -1.84
    
    -1.81
     startling
    -1.77
    剮
    -1.76
    POSITIVE LOGITS
    3
    2.16
    5
    2.09
    4
    1.91
    7
    1.88
    genheiten
    1.87
    1
    1.85
    9
    1.82
    8
    1.80
    6
    1.74
     had
    1.73
    Activations Density 0.000%

    No Known Activations