© 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. 116818
    Prev
    Next
    INDEX
    Explanations

    percentages and proportions

    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
     thousands
    -1.30
     hundreds
    -1.13
     Thousands
    -0.98
     tens
    -0.94
    Thousands
    -0.92
     billions
    -0.89
     Hundreds
    -0.88
     milhares
    -0.88
     一般
    -0.85
    Hundreds
    -0.85
    POSITIVE LOGITS
     (
    1.52
     $(
    1.38
     }(
    1.23
    $(
    1.10
     frequency
    0.99
    tská
    0.91
     (%)
    0.91
    Frequency
    0.91
     Frequency
    0.88
     were
    0.87
    Activations Density 0.101%

    No Known Activations