© 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. 22-GEMMASCOPE-RES-131K
    7. 129398
    Prev
    Next
    INDEX
    Explanations

    cooking meatvisible withinsimple andincreased numbernew windowincreasing Mnkeeping journalists

    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_22/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
    eapon
    -0.91
     rembourse
    -0.90
    nemy
    -0.87
     particules
    -0.83
     německ
    -0.81
    ꜆
    -0.81
     aquello
    -0.81
    řel
    -0.80
     Brooklyn
    -0.79
     cardboard
    -0.78
    POSITIVE LOGITS
     environments
    1.23
     environment
    1.16
     exposure
    1.13
     estamos
    1.12
    אַ
    1.00
     location
    0.93
     platforms
    0.92
    新しい
    0.91
     formats
    0.91
     Lainnya
    0.90
    Activations Density 0.105%

    No Known Activations