© 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. 34-GEMMASCOPE-RES-131K
    7. 65789
    Prev
    Next
    INDEX
    Explanations

    Herb Chambers

    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_34/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
     allem
    -0.83
     упаковке
    -0.82
    hemp
    -0.80
    ALLAS
    -0.79
    fread
    -0.79
     (_
    -0.79
     queer
    -0.77
    NotImplemented
    -0.77
    办理
    -0.77
     coal
    -0.77
    POSITIVE LOGITS
    GOOGLE
    1.04
     Google
    0.96
     überprüft
    0.94
    czes
    0.93
    google
    0.90
     FLAGS
    0.87
     Gmail
    0.86
     scrapbooking
    0.86
     hibern
    0.85
     wiederholt
    0.84
    Activations Density 0.057%

    No Known Activations