© 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. 4290
    Prev
    Next
    INDEX
    Explanations

    competitive field quality

    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
    genome
    -0.90
    ulaires
    -0.87
    <0xB7>
    -0.82
    >-</
    -0.81
    ोंने
    -0.80
     رسمی
    -0.79
    TOUCH
    -0.79
    itizing
    -0.78
    broek
    -0.77
    ajiban
    -0.77
    POSITIVE LOGITS
     field
    2.28
     crowded
    1.79
     fields
    1.73
     loaded
    1.59
     talent
    1.37
    field
    1.34
     stacked
    1.34
     depth
    1.28
    Field
    1.27
     Field
    1.26
    Activations Density 0.042%

    No Known Activations