© 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. 90534
    Prev
    Next
    INDEX
    Explanations

    quantities and counts

    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
    谙
    -0.96
    vaart
    -0.91
    ❮
    -0.87
    titleMargin
    -0.82
     أجل
    -0.82
    导演
    -0.80
     incomes
    -0.80
    isdigit
    -0.79
    бив
    -0.79
    isset
    -0.78
    POSITIVE LOGITS
     amount
    2.44
     number
    1.77
     percent
    1.72
     how
    1.68
     dollars
    1.64
     Amount
    1.64
     days
    1.61
     total
    1.57
     hours
    1.56
     time
    1.55
    Activations Density 0.054%

    No Known Activations