© 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. 23521
    Prev
    Next
    INDEX
    Explanations

    channels

    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
     隊
    -0.77
    roch
    -0.76
    덮
    -0.75
    Vanity
    -0.73
     कुल
    -0.73
     optimis
    -0.71
     ホール
    -0.69
    ciling
    -0.69
    nyk
    -0.69
    紜
    -0.69
    POSITIVE LOGITS
     channel
    1.26
     channels
    1.07
     Channel
    1.05
    CHANNEL
    1.03
    channel
    0.98
    Channel
    0.93
     CHANNEL
    0.90
    Channels
    0.88
     Channels
    0.85
     Global
    0.83
    Activations Density 0.019%

    No Known Activations