© 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. 50012
    Prev
    Next
    INDEX
    Explanations

    listing items

    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
     must
    -0.97
    onore
    -0.95
     moor
    -0.81
     мон
    -0.80
     monoc
    -0.80
    Cores
    -0.79
    Mora
    -0.76
     bool
    -0.75
    ؟
    -0.75
     بگو
    -0.74
    POSITIVE LOGITS
     would
    1.03
    Boy
    0.94
     Moy
    0.93
    obox
    0.90
     Bowman
    0.89
     Bradley
    0.89
    Bow
    0.88
     Fowler
    0.88
     Boyd
    0.87
    Fox
    0.85
    Activations Density 0.010%

    No Known Activations