© 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. 22-GEMMASCOPE-RES-131K
    7. 67692
    Prev
    Next
    INDEX
    Explanations

    Highway / City MPG

    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
     dessinée
    -0.99
    അ
    -0.93
     зелены
    -0.93
     it
    -0.92
    ее
    -0.92
     conectados
    -0.91
     years
    -0.90
    ВОД
    -0.89
    их
    -0.88
    век
    -0.88
    POSITIVE LOGITS
     again
    1.07
    igned
    1.04
    Voltaje
    0.99
    bourhood
    0.99
     opnieuw
    0.98
    際には
    0.98
    dhury
    0.96
     ibid
    0.96
     [''],
    0.96
    nasi
    0.95
    Activations Density 0.001%

    No Known Activations