© 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. 69885
    Prev
    Next
    INDEX
    Explanations

    Jab and related sequences

    np_acts-logits-general · gemini-2.5-flash-lite

    names or words beginning with "Jab" or similar syllables.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    样式
    -0.75
     cli
    -0.75
    δες
    -0.73
     tundra
    -0.71
    Items
    -0.69
    vb
    -0.67
    calibration
    -0.66
    atika
    -0.66
    平面
    -0.66
     tomb
    -0.66
    POSITIVE LOGITS
     Jab
    1.32
    Jab
    1.14
    jab
    0.90
     jab
    0.89
     Janet
    0.78
    operand
    0.75
     trouw
    0.75
    cshtml
    0.74
     lange
    0.72
    TabBar
    0.72
    Activations Density 0.022%

    No Known Activations