© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 49962
    Prev
    Next
    INDEX
    Explanations

    cloudfront, division, immunotherapy, women, mech

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

    software and web-related technical terms like 'cloudfront', 'division', 'display', and 'immunotherapy'.

    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
    Friends
    -0.91
    kyr
    -0.91
    hever
    -0.82
    ровала
    -0.79
    ньому
    -0.78
    EqualsAnd
    -0.78
    WithIdentifier
    -0.78
    URLConnection
    -0.77
    回し
    -0.77
     terjangkau
    -0.76
    POSITIVE LOGITS
    析
    0.83
    ولايات
    0.78
     turg
    0.76
    chown
    0.75
     aceptas
    0.75
    痫
    0.75
    wahl
    0.73
    Commodity
    0.71
    foria
    0.71
    Bele
    0.71
    Activations Density 0.000%

    No Known Activations