© 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. 75701
    Prev
    Next
    INDEX
    Explanations

    filter

    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
     Vaticano
    -0.83
     Thoma
    -0.72
    掃除
    -0.70
    Screenshots
    -0.68
    Decimals
    -0.68
     トート
    -0.67
     screenshots
    -0.67
     Speakers
    -0.67
     Habits
    -0.66
    Tomas
    -0.66
    POSITIVE LOGITS
     filter
    3.59
     filters
    3.58
    filter
    3.05
    filters
    2.95
     Filters
    2.84
    Filter
    2.84
     Filter
    2.81
    Filters
    2.58
    FILTER
    2.50
    滤
    2.33
    Activations Density 0.027%

    No Known Activations