© 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. 7199
    Prev
    Next
    INDEX
    Explanations

    class definitions and methods

    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
    eronau
    -1.11
    nemia
    -1.03
     During
    -1.02
    semibold
    -0.98
     various
    -0.97
     Պ
    -0.96
     M
    -0.94
    itzenden
    -0.91
    攫
    -0.89
     H
    -0.88
    POSITIVE LOGITS
    ↵↵↵
    1.59
    ↵↵↵↵
    1.56
    ↵
    1.52
    ↵↵
    1.48
    ↵↵↵↵↵↵↵↵↵↵
    1.41
    ↵↵↵↵↵↵↵
    1.34
    ↵↵↵↵↵
    1.33
    ↵↵↵↵↵↵
    1.26
    ↵↵↵↵↵↵↵↵
    1.25
    ↵↵↵↵↵↵↵↵↵
    1.23
    Activations Density 0.009%

    No Known Activations