© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 69879
    Prev
    Next
    INDEX
    Explanations

    rich description

    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
    些什么
    -0.90
    The
    -0.88
     вслед
    -0.88
     rah
    -0.85
    スクリーン
    -0.84
     marvels
    -0.84
     enceinte
    -0.83
     heroes
    -0.82
     चि
    -0.82
     chiffres
    -0.82
    POSITIVE LOGITS
    rich
    2.02
     rich
    1.97
     Rich
    1.73
    Rich
    1.69
    RICH
    1.64
     RICH
    1.45
    ochet
    1.42
     richer
    1.38
     richness
    1.34
    riched
    1.29
    Activations Density 0.020%

    No Known Activations