© 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. 26554
    Prev
    Next
    INDEX
    Explanations

    programming, names, punctuation, wins

    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
    的区别
    -1.03
     vostri
    -0.96
    breviations
    -0.96
    Bulgaria
    -0.94
    Bole
    -0.93
    $",
    -0.93
    墘
    -0.91
     pontific
    -0.90
     prodig
    -0.88
     veng
    -0.88
    POSITIVE LOGITS
     hingga
    0.92
     inocente
    0.88
     economic
    0.88
     business
    0.87
    dns
    0.86
    if
    0.86
    телям
    0.84
     our
    0.84
     såg
    0.83
     adipis
    0.83
    Activations Density 0.061%

    No Known Activations